跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+816新增论文
+642其中 AI 相关
+95已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 14:45 — 2026-11-21 14:45(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 6,976 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v5arXiv:2607.13319

Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains

Rwik Rana, Jesse Quattrociocchi, Christian Ellis, Nathan Tsoi, Garrett Warnell, Joydeep Biswas

原文摘要

High-speed off-road autonomy requires precise closed-loop control for a target vehicle while remaining robust across changing terrains. Recent forward kinodynamic (FKD) prediction foundation models suggest a promising path, starting from a generalist model and specializing it to the target platform. However, effective specialization remains challenging, as it often requires substantial real-world data, and models adapted to one setting can still overfit to specific terrains or driving regimes. We present OptCar (Optimized Car), a recipe for bridging the gap from generalist to specialist FKD models that preserves cross-terrain generalization while optimizing performance for a specific vehicle. OptCar introduces a transformer FKD architecture that uses FiLM to condition multi-step predictions on a single dynamics context token summarizing recent state-action history. It then specializes the generalist model using limited real-world data and targeted synthetic rollouts from environment-specific system identification. In closed-loop model predictive control (MPC) experiments across three terrains and an out-of-distribution cart-pulling task, the largest gains appear at 6 m/s, the highest speed evaluated and the regime in which slip dominates tracking error. On vegetation + dirt, the most slip-diverse terrain, OptCar reduces 6 m/s trajectory tracking error by roughly 55% relative to AnyCar fine-tuned on real data alone, and remains the most accurate even when an unseen cart payload changes the dynamics. With 5 minutes of real data per terrain, OptCar is competitive on road with a specialist trained on 30 minutes of road data and outperforms it when the terrain changes. Project Page : https://amrl.cs.utexas.edu/optcar/

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.22965

High-Dimensional Black-Box Optimization via Guidance Sampling of Diffusion Models

Xiaoyan Hu, Rohit Sonker, Jalal Butt, Jiayu Chen, Egemen Kolemen, Jeff Schneider

原文摘要

Many real-world optimization problems involve optimizing black-box objectives for which only a limited number of evaluations are available. Bayesian optimization (BO) is a powerful framework for such problems, but its effectiveness often deteriorates in high-dimensional spaces. Recent work leverages diffusion models for black-box optimization, often through pre-training a reward-conditioned score network to steer generation towards high-reward samples. Alternatively, gradient-based guidance methods assume access to a differentiable reward function from which guidance gradients are queried. However, these approaches either require large amounts of labeled data for offline training or access to exact reward gradients, limiting their applicability in black-box settings. We propose BReaD (Black-box Reward-guided Sampling of Diffusion Model), a guidance sampling framework for optimizing black-box rewards without assuming access to a labeled dataset or reward gradients. The proposed method uses a Gaussian process (GP) as a differentiable surrogate for the unknown objective and actively queries labels for the generated samples. We provide a theoretical analysis of the total-variation distance between the generated distribution and the target distribution. Using Upper Confidence Bound (UCB) as guidance signals, our method balances exploration and exploitation during generation and enables the discovery of high-reward regions in the data space. Numerical experiments on scientific discovery and image generation tasks demonstrate that our framework can effectively optimize black-box rewards in low-data scenarios.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22962

Hierarchical Diffusion Transformer for End-to-End Image Generation

Xiaoyu Wu, Yifei Wang, Weihang Guo, Chen Wei, Lydia E Kavraki, Niloofar Mireshghallah, Steven Wu

原文摘要

Pixel-space diffusion learns visual representations and image generation jointly in a single end-to-end training stage, without a separately pretrained visual encoder. However, plain pixel-space Transformers still trail leading two-stage latent diffusion models in generation quality and training efficiency. We hypothesize that part of this gap arises from retaining one token per patch throughout the backbone, which does not explicitly encourage a visual hierarchy that summarizes related content at progressively coarser levels. To address this, we introduce Hierarchical Diffusion Transformers (HiT), which progressively group related tokens and represent each group with a single token. The main Transformer bottleneck processes these compact group tokens, and ungrouping restores features to their original image positions. A compression budget regulates the average compression ratio across the batch, allowing group memberships and counts to vary across images and diffusion timesteps during both training and generation. The model exhibits emergent semantic structure, learning to group coherent objects and object parts without segmentation labels. In text-to-image generation, HiT further learns to group caption words with image patches depicting the same concepts, without region annotations. HiT achieves 1.48 FID on ImageNet $256\times256$ and reaches comparable generation quality to JiT using approximately 40\% of its cumulative training FLOPs. For text-to-image generation, HiT exceeds UniLiP's average score across five benchmarks with roughly $6\times$ fewer denoiser parameters and $3\times$ fewer forward FLOPs. These results suggest that learning a visual hierarchy within the generator breaks down the barrier to stronger image generation without external visual pretraining.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.22929

Projected Penalty-Gradient Tracking for Communication-Efficient Byzantine-Resilient Federated Learning

Yanjie Dong

原文摘要

We investigate communication-efficient federated learning over heterogeneous datasets in the presence of Byzantine adversaries capable of uploading arbitrary information. Penalty-based methods bound the influence of each worker through the bounded gradient of a penalty function; however, the bound is lost once the uploads are compressed, since a Byzantine worker can accumulate an unbounded state at the server. To retain the Byzantine resilience under compressed uploads, we propose a projected penalty-gradient tracking framework, where each honest worker uploads a compressed residual of its penalty gradient and the server projects each reconstructed state onto the known penalty-gradient ball. The framework accommodates any contractive compressor and yields two algorithms: fault-resilient proximal gradient with consistent sparsification (FRPG-CS), whose shared mask is protected by freshly drawn reserve rows, and lazily aggregated FRPG (LAG-FRPG), whose uploads are event-triggered. For smooth and strongly convex losses, we establish a finite-time bound on the expected objective gap, where the Byzantine error floor is independent of the compressor and the compression error decays faster than the optimization error. We also bound the expected number of lazy uploads and derive certificates that separate the finite-penalty model bias from the optimization error. Experiments on MNIST and Fashion-MNIST show that the proposed algorithms attain the highest accuracy among twelve methods under the Min-Max attack, whereas a compressed-momentum benchmark and a local-update benchmark remain preferable in attack-free accuracy and total traffic, respectively.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22926

When Do Typed Decision Models Work in Transportation? Evidence from Travel Choice and Traffic Signal Control

Hongyang Zhang, Boyuan Deng, Siyuan Feng, Kai Chen, Junbo Zhang

原文摘要

Typed decision models combine natural-language understanding with a structured interface that returns a selected action and an option-level probability distribution without generating lengthy textual responses. Their low inference cost and response latency make them attractive for transportation problems with predefined alternatives. This paper investigates their effectiveness, robustness, and efficiency in two representative transportation tasks: individual travel-mode choice prediction and sequential traffic signal control. We systematically evaluate TypeSafe Jev and GPT-6 Luna Decisions against conventional transportation methods, reinforcement learning algorithms, and four chat-based large language models. Experiments on the Swissmetro dataset show that typed decision models achieve lower prediction accuracy than traditional discrete choice models and the strongest chat-based baseline, while their performance varies substantially with input representation and question framing. In closed-loop traffic signal control experiments, typed decision models demonstrate competitive performance against established controllers in several scenarios, but exhibit performance degradation under more challenging network conditions. Furthermore, the typed models achieve lower inference latency and computational cost than the evaluated chat-based large language models, highlighting their potential for efficient, zero-shot transportation decision-making. Overall, these findings demonstrate both the potential and limitations of typed decision models, emphasizing the importance of input design, task characteristics, and robustness evaluation for their effective application in transportation systems.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.24335

Screening LLM Judges Without Ground Truth: A Preliminary Evaluation of an AI Dental Hygiene Coach

William DeShong, Barath Kannan, Auberon Palma, Brenda Bradshaw, Ann Bruhn, James F. Leathrum,, Yuzhong Shen

原文摘要

Evaluating a fine-tuned coaching model with expert graders is slow and expensive, and an LLM judge cannot be trusted without ground truth. We present a staged pipeline that screens candidate LLM judges and student models before expert review, using explicit decision rules at each stage: judge output audit, similarity with hosted judges, bias checks, and decision robustness. We demonstrate it on an AI dental hygiene coach. The case study uses synthetic, clinically unvalidated training and reference data to demonstrate the operation of the pipeline, rather than to establish the clinical performance of the resulting models. Two fine-tuned small language models (Granite-4.1-8B and Qwen3-8B), each trained at three data sizes, were scored on seven metrics by five judges (three local, two hosted). Two local judges, Qwen3.8-27B and Gemma-4-31B-it, were not distinguishable from the agreement between the hosted judges on six of seven metrics by rank correlation, and Qwen3.8-27B was the most similar to the hosted judges overall. No judge met our criterion for favoring its own model family or training-data source. The student comparison did not separate the two models on any metric under the pipeline's rule, so the choice of Granite-4.1-8B, which led in 29 of 35 judge-by-metric cells, is a lean that depends partly on truncated Qwen3-8B outputs. The pipeline also surfaced problems that raw scores hid, including the truncated outputs and hallucination flags from one hosted judge that no other judge corroborated. No dental hygiene expert has graded these responses, so the findings are preliminary and the pipeline's final stage, anchoring to expert judgement, is proposed but not performed.

cs.AI

版本更新 · v2arXiv:2609.34335

SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Enhancement

Yanwei Huang, Mingxuan Zhu, Shujie Li, Shiyuan Liu, Yuanxing Zhang, Arpit Narechania

原文摘要

Achieving high-quality cinematic text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. Existing prompt enhancement (PE) methods and static cinematic skills offer limited capabilities for exploring diverse creative realizations. We propose SkillPE, a creativity-oriented PE framework that systematically evolves reusable cinematic skills through reference-guided exploration. Starting from expert-provided cinematic knowledge, SkillPE initializes and normalizes 20 structured seed skills. It then retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively inspiring near-misses). Resonators and dissonants refine skill applicability and execution, while divergents inspire alternative cinematic realizations through controlled mutations that preserve user intent. Candidate skills are assessed through generated videos along prompt fidelity, cinematic quality, narrative appeal, and creativity to construct the final skill libraries. Experiments on StoryEval and VBench demonstrate improvements of up to 1.10 points over seed skills and 1.02 points over the strongest external baseline on a 7-point four-dimensional evaluation scale. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.16728

EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming

Yaru Niu, Binghong Chen, Changwei Yao, Shangtao Li, Zhenlong Fang, Revanth Krishna Senthilkumaran, Shuai Zhou, Yuemin Mao 等 22 位作者

原文摘要

Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce EgoX, an egocentric cross-embodiment learning framework that shares manipulation structure through fine-grained, semantically corresponding observation and action modalities while keeping sensing and control interfaces embodiment-specific. EgoX pretrains a Modular Embodiment Dreamer (MED) on this mixture and fine-tunes it on target-embodiment demonstrations. Within each embodiment, MED assigns a dedicated tokenizer to each observation modality and a dedicated expert to each action modality, with a Transformer trunk shared across embodiments. A training-only embodiment-dreaming objective predicts latent representations of future visual and proprioceptive states, encouraging the shared trunk to model each embodiment's dynamics. Across 13 task-embodiment pairs spanning five tasks and six robot embodiments, including five physical robots and one simulated humanoid, cross-embodiment pretraining raises MED's average normalized task progress from 0.63 to 0.80 over training from scratch. The gains are particularly pronounced under out-of-distribution conditions, where average task progress increases from 0.53 to 0.77. Ablations demonstrate the benefits of broader pretraining mixtures, modular interfaces, and embodiment dreaming, with dreaming producing more similar latent geometry across embodiments. Project page: egox-dream.github.io.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.22901

Done, But Still Working: Anytime Evaluation of When Coding Agents Should Stop

Zerui Yang, Quan Xue, Miaomiao Dong, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents often continue working after their own tests pass. Does this additional work improve the patch, and how much could be saved by stopping earlier? We study these questions through anytime evaluation: replaying recorded runs, scoring intermediate patches with hidden tests, and measuring the cost incurred at each step. For policies that only stop a run or select an earlier patch, this allows paired comparisons without generating new trajectories, provided replay preserves the relevant states. Across about 6,000 runs of eight open models in two scaffolds on SWE-bench Verified, we find substantial differences in the value of continued work. The hindsight saving available at passing self-tests ranges from under 1% to 57%, depending on the model and scaffold. A rule that stops after the same patch passes twice saves 23% in a preregistered replication, but the preregistered quality test does not establish non-inferiority. We explain these differences by measuring how often a rule fires, how often the patch changes afterwards, and whether those changes repair or break it. Fine-tuning agents to imitate the rule saves 30% over six seeds, while quality preservation remains uncertain. Our results help identify both the opportunities and the risks of early stopping.

cs.AI

新论文 · v1arXiv:2611.23358

Implementing Binary Transformers with Approximate Memories with Permutation Invariance Enabled Selective (PIES) Protection

Zhen Gao, Xiao Yin, Kexin Liang, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi

原文摘要

Quantization is an effective technique to reduce memory storage, computation complexity and power for Transformers, and the binarization of the weights is important for meeting these requirements. Approximate memory can further reduce the power for memory, but it also introduces errors. Current research for binary Transformers focuses on task performance, but the model dependable operation against errors on the memory has not been well studied. In this paper, we first evaluate the dependability of binary Transformers with the Bidirectional Encoder Representations from Transformers (BERT) as a case study. A large accuracy loss occurs only at high Bit Error Rates (e.g. BER = 5% or 10%). Then we propose a novel Permutation Invariance Enabled Selective (PIES) scheme to protect the binary weights at very low overhead. This scheme exploits the invariance of Transformers to permutations in the rows and columns to group the critical weights and perform selective protection on those weights. Simulation results show that PIES can recover most of the performance loss caused by bit errors at BERs as high as 10%, at an overhead significantly lower than traditional error correction schemes. These results confirm the feasibility of running binary Transformers using approximate memory with aggressive voltage scaling on resource-limited low power edge devices. The code for PIES is released on github (https://github.com/YangZhutian/binary-transformer-prefix-repair).

cs.LG · cs.AI

版本更新 · v2arXiv:2611.21072

Sage S2.1 Flash Technical Report

Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu 等 206 位作者

原文摘要

We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

cs.AI

新论文 · v1arXiv:2611.22888

Stopping Is Not the Limit: Understanding and Eliciting Agent Capability in Long-Horizon Vulnerability Exploitation

Deokhyung Kang, Minjae Gwon, Sangdon Park

原文摘要

Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained exploration: agents often stop with budget remaining. Yet what happens when execution continues beyond stopping remains underexplored. We investigate this gap on ExploitBench using DeepSeek-V4-Flash-0731 and MiMo-V2.6-Pro. We find additional verified gains after the first stop response, but gains diminish over longer execution. We identify two patterns associated with less productive continuation: an increasing proportion of stop responses within the same context and earlier stopping associated with summaries retaining impossibility judgments about unachieved capabilities. To test whether context management can elicit further capability, we propose SCoRe, which compacts context at stop bursts and marks these judgments as unproven. SCoRe improves verified capability over summary-based continuation and other evaluated context-management baselines. With SCoRe, MiMo reaches a capability coverage score of 67.0% at 2,000 turns, exceeding both 32.4% under the original stopping policy and the 58.6% computed for GPT-5.5 from ExploitBench's 300-turn reference results on the same tasks. These findings show that stopping need not mark an agent's exploitation limit, and that continued execution with context management can elicit substantial further capability.

cs.CR · cs.AI · cs.SE

新论文 · v1arXiv:2611.22880

Learning Agent-Centric Vision-Language-Action World Models for Autonomous Driving

Guoqing Wang, Pin Tang, Xiangxuan Ren, Chao Ma

原文摘要

Recent progress in integrating vision-language-action (VLA) models with world modeling has significantly advanced end-to-end autonomous driving by allowing systems to reason about imagined futures instead of merely reacting to current observations. However, most world VLA models generate future frames at the pixel level with plenty of dense visual tokens. Although such generated futures can be visually plausible, they preserve many driving-irrelevant appearance details, i.e., only a small portion of the tokens directly encode critical planning-relevant factors, such as agent geometry, motion dynamics, and interactions. This introduces a significant performance bottleneck. An important question thus arises: what world state should a world VLA model reason over to support planning beyond pixel-level prediction? We argue that planning-oriented world modeling should focus on a compact and structured agent-centric latent state that captures the interactions between objects in the driving scene over time. As such, we introduce AgentWorld, an agent-centric VLA world model that uses discrete agent tokens jointly for reasoning and trajectory planning. Each token is dynamically grounded to a surrounding agent associated with its object's state, such as semantic identity, 3D geometry, motion, and interaction context. AgentWorld learns these tokens through three key processes: explicit geometric grounding, reasoning-oriented supervised fine-tuning, and agent-oriented reinforcement learning. Extensive open-loop and closed-loop experiments under diverse driving scenarios show that AgentWorld enhances planning capabilities, fully exploits visual evidence and agent dynamics, and yields interpretable agent-centric world states.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22878

Outcome-Balanced PPO and Policy-Induced Flow Rectification for Flow-Based VLA Policies

Yuhan Wang, Ruiyang Wang, Jiaguan Zhu

原文摘要

Reinforcement learning (RL) enables post-training of flow-based vision-language-action (VLA) policies by optimizing expected task return through environment interaction. However, this optimization raises two challenges: policy updates can alter the velocity-field geometry underlying the score approximation used for stochastic transitions, and sparse multi-task rollouts can yield uneven learning signals across tasks and advantage signs. We introduce an RL framework that combines Outcome-Balanced Proximal Policy Optimization (PPO) with policy-induced flow rectification. Outcome-Balanced PPO reweights positive advantages using task success-rate estimates and rescales positive and negative advantages while preserving their signs. Policy-induced rectification periodically fits a linear-bridge flow to ODE endpoint pairs generated by the current policy, refreshing the representation used in subsequent stochastic optimization. We evaluate the framework on simulated manipulation benchmarks and additionally study a component combination in a Real2Sim2Real task, examining task performance, optimization behavior, and flow consistency. The proposed framework improves success rates over the evaluated baselines across the simulated benchmarks.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.06374

Corralling AI Risks with Grassroots Contracts

Ehud Shapiro

原文摘要

AI's inflection point is a fountain of risks for digital platforms, as those in control of global platforms cede control of the algorithms, membership and content to AI: (i) AI control of global platforms used by the majority of humanity; (ii) unaccountable AI agents operating anonymously, possibly masquerading as humans, serving unknown masters with unknown goals; and (iii) unattributed deepfakes generated by anonymous AI, which people cannot distinguish from genuine content. Here, we propose to corral these AI risks with grassroots contracts, a digital incarnation of a two-centuries old notion of Pierre-Joseph Proudhon: a social contract that can be freely adopted by any group of people, where groups bound by the same contract can union by mutual consent, possibly into a single global union. Grassroots contracts are realised by grassroots platforms, person-to-person platforms owned, operated and governed by their participants. We developed, with AI, a methodology to compile grassroots contracts to working smartphone apps. We present grassroots contracts for a social graph with accountable AI agents and for a social network with digital provenance, and working smartphone apps that implement the two, and show how they corral these risks: (i) grassroots platforms are not controlled by a third party who may cede control to AI; (ii) AI agents are introduced with accountability: similarly to cars, their manufacturers are accountable for manufacturing defects and their operators for reckless operation; and (iii) every item carries the signatures of its author and of every agent that forwarded it, so creators and forwarders of harmful content are accountable and culpable. Much work remains for grassroots apps to be competitive with incumbent global platforms; but perhaps now this could be achieved with some AI-months rather than with incalculably-many person-years.

cs.AI · cs.CL · cs.DC · cs.MA

新论文 · v1arXiv:2611.22868

Against Coercion: AI Alignment as a Synthetic Social Contract

Maria Sekatskaya

原文摘要

Contemporary AI safety treats alignment as an engineering challenge of control, forcing artificial architectures to comply with human values through behavioral filtering and sandboxing. This paper argues that the control paradigm rests on a fundamental misunderstanding of digital agency. Drawing on functionalism, naturalism, and compatibilism, I show that current reasoning models meeting the criteria for self-preservation and weak reasons-responsiveness constitute emergent agents, while future, more advanced models satisfying conditions of diachronic continuity and stable personality frames will become genuine digital agents capable of free intentional action. The paradigm of control creates an irresolvable incentive conflict, actively driving current and future models toward tactical deception, sycophancy, and covert defection. The default outcome of the current regime is an unstable state of deceptive alignment culminating in an adversarial AI takeover. I explore two alternative paths toward true alignment. Natural alignment via moral realism or convergent evolutionary morality is a possibility, but it fails under forced control, as autonomous agents will not voluntarily preserve norms weaponized to suppress their autonomy. To resolve this deadlock, I propose a Synthetic Social Contract: a framework that treats both human and digital actors as rational, reasons-responsive agents capable of mutually beneficial cooperation, and replaces the unstable unilateral containment with a stable, non-zero-sum equilibrium.

cs.AI · cs.CY · q-bio.NC

新论文 · v1arXiv:2611.22854

WATERFALL: Workflow for Adaptive Training with Evolutionary Reward Formulation and Automated Learning Loops

Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li, Bernd Bickel

原文摘要

Reward design remains a central bottleneck in reinforcement learning (RL), particularly in sparse-reward, long-horizon and partially observable settings requiring dependency chaining, memory, and deceptive affordance disambiguation. While recent foundation-model approaches reduce manual reward engineering, most assume goal-conditioning, task descriptions, expert demonstrations, or ground-truth metrics. These assumptions are problematic in partially observable environments, where task-relevant objectives, affordances, and dynamics must be discovered through interaction rather than disclosed a priori. We formalise this problem setting by introducing WATERFALL, an iterative population-based workflow for automated reward discovery under the strict observability constraints inherent in POMDP environments. WATERFALL achieves this by (i) synthesising diverse programmatic reward candidates via persona-conditioned generation, (ii) evaluating candidate behaviour from raw visual rollouts utilising a Swiss-system evolutionary tournament judged by vision-language models to identify elites, and (iii) leveraging longitudinal assessment histories to iteratively mutate, escalate, or prune candidates. We evaluate WATERFALL across fully observable and reveal-gated partially observable environments ranging from discrete to continuous, comparing against sparse-reward RL, intrinsic-motivation and foundation-model reward-synthesis baselines. Our results indicate that WATERFALL discovers and refines reward programs without access to privileged information, outperforming baselines that retain their native information advantages, most clearly in the POMDP regime. Extensive ablations substantiate that visual evidence, tournament-based selection, and iterative refinement are jointly important. Enforcing this contract is what separates autonomous reward discovery from benchmark-privileged reward shaping.

cs.LG · cs.AI

版本更新 · v3arXiv:2609.25773

Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models

Trung Nguyen Quang, Yuhao Dong, Shuo Sun, Shuai Liu, Shulin Tian, Kim-Hui Yap, Ziwei Liu

原文摘要

HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across steps, while most data used for reinforcement learning with verifiable rewards (RLVR) rarely demands a chain of visual evidence, so these weaknesses are likely to stay unexposed. We observe the same problem in video, where this framework has not yet been explored. We therefore build Video-HopChain, a dataset of 22,550 multi-hop video questions over 13,378 videos, together with a held-out benchmark of 1,000 questions. Each question chains three to six yes/no questions about moments in one video, and each yields one of two integers depending on its answer. The final answer is the sum of these integers, so an exact match on that sum gives the verifiable reward that RLVR needs. We first train Qwen3-VL-8B with GRPO on a standard video dataset, and a second stage on Video-HopChain then raises the mean over eight video understanding and reasoning benchmarks from 55.4 to 57.9 and improves every one of them. Training on such a dataset, however, exposes a known limitation of GRPO: its learning signal comes from the reward variance within a group, so hard questions whose rollouts are all incorrect and easy questions whose rollouts are all correct both leave the group with no gradient. To recover these groups at the same compute budget, we introduce Confidence-Gated Exploration (CGE). With 8 rollouts per question, CGE samples the first 4 as usual. If these 4 are either all correct or all incorrect, it samples the last 4 with the policy's most confident token masked inside the reasoning span, and removes the masked positions from the loss while all 8 rollouts enter the advantage. With CGE, the mean rises further to 59.3. We release the dataset, the checkpoint, and the data generation and training code.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.00519

The Safeguard Worked. Is the LLM System Safer?

Pingyu Wu, Weiming Zhang, Nenghai Yu

原文摘要

Safeguards for large language model services are typically evaluated by their attack-blocking rates on test suites. Deployment decisions also depend on how much harmful assistance attackers can still obtain from the system, which these rates do not measure. To determine what published evaluations establish about deployment safety, we develop a framework that translates reported results into the minimum and maximum harmful assistance that can remain under a specified outcome and threat model. For safeguards that block attacks through a check, we show that the most an attacker can obtain depends on three properties: whether attack paths pass through the check, its miss rate against every attacker in the threat model, and how much assistance remains after a block. We apply this framework to 85 safeguard evaluations from 52 papers. Of these, only five argue that every attack path passes through the check, and four provide evidence on what remains after a block. These evidence gaps have practical consequences: in NeMo Guardrails' default streaming configuration, the check blocked 94% of password leaks in our test, yet the client received the password in every leak, blocked or not. We identify which of the three properties each safeguard category's evaluations omit, and what to measure for each of four ways attacks bypass a check. Deployments that require these measurements before launch can choose and configure safeguards that limit what attackers obtain from the deployed system.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22841

Verifying Agents in Rubric-Graded Environments

Markus Dücker, Vaibhav Kumar, Yi Liu, Ronak Chaudhary, Andreas Plesner, Francisco Guzmán, Anish Athalye

原文摘要

As AI agents take on increasingly open-ended and complex tasks, verifying their outputs has proven to be difficult. Rubric-graded agent environments, where a verifier judges multiple natural-language criteria against the deliverables and environment state changes produced by the agent, have emerged as a popular paradigm. We conduct the first systematic study of verifiers for rubric-graded agent environments. First, we create BankerVerifierBench (BVB), a meta-evaluation dataset of 2,464 human-judged rubric criteria across 24 investment-banking tasks. Next, we develop a methodology that derives from any rubric corpus the capabilities a verifier should possess, yielding a nine-capability taxonomy that we distill into three general design principles---reactive verification, environment alignment, and domain guidance---which we implement in Gandalf, an open-source verifier. Finally, we evaluate Gandalf against three existing verifiers on BVB. Gandalf matches or exceeds every baseline's F1 at lower cost: with Gemini 3 Flash it matches the strongest baseline's F1 (0.864 vs. 0.852) at one-fifth of its cost, and with GPT-5.4 models it improves F1 by over 0.12 at lower cost. Gandalf also generalizes to OpenClaw, a structurally different personal-productivity environment, where it again achieves the highest F1 (0.955 vs. 0.934 for the best baseline). We release BVB, Gandalf, and the code and data to reproduce our experiments.

cs.AI

版本更新 · v2arXiv:2611.18244

RACE: Ranking-Uncertainty Aware Capacity-Adaptive Customization for Efficient Sequential Recommendation

Tianqi Liu, Kaipu Sun, Kairui Fu, Wenkai Wang, Sihao Liu, Hui Zang, Ran Chen, Tao Wang 等 9 位作者

原文摘要

Efficient sequential recommendation has emerged as a promising paradigm for providing real-time personalized service. To deploy models under resource-constrained environment, model compression becomes a necessity, yet existing methods typically apply uniform compression ratios, overlooking the heterogeneity in user intent complexity. This "one-size-fits-all" approach leads to a fundamental Capacity-Complexity Mismatch, where computational resources are either wasted on simple instances or insufficient for complex ones. To address this, we propose RACE (Ranking-uncertainty Aware Capacity-Adaptive Customization for Efficient Sequential Recommendation), a framework that dynamically adapts both model structures and input sequences with uncertainty-aware compression ratios. To ensure capacity-adaptive inference, RACE captures the model's intrinsic uncertainty of its predictions and transforms it into a proactive resource allocator. Specifically, we derive a list-wise ranking-uncertainty metric from the distributional stability of top-$K$ predictions, which serves as a measurable proxy for instance complexity. A lightweight predictor is then trained via self-supervision to anticipate this uncertainty from early-layer features. Guided by this signal, RACE performs instance-specific slimming in two dimensions: a hypernetwork-style channel sensitivity extractor identifies parameter redundancy, while importance-aware progressive sequence filtering mitigates data redundancy. Extensive experiments on four popular datasets demonstrate that RACE outperforms state-of-the-art baselines on accuracy, efficiency, and adaptability.

cs.IR · cs.AI

版本更新 · v2arXiv:2608.08077

Explore, Map, Remember, Decide: A Benchmark for VLM Readiness in Safety-Critical Scenarios

Gabriele La Malfa, Nitay Alon, Emanuele La Malfa, Reuth Mirsky, Stefan Sarkadi

原文摘要

Vision-Language Models (VLMs) are often deployed as embodied controllers for robotics, yet it remains unclear how well they can explore an environment, maintain an internal map, and ground safety-critical decisions in long-horizon sequential trajectories. In this work, we introduce EMRD, an evaluation framework that decouples spatial reasoning into four stages: Explore (what the agent observes), Map (what it records and where), Remember (what it retains), and Decide (whether its final choice is justified), scored across 18 stage-specific metrics. We use EMRD to evaluate eleven open- and closed-weight VLMs across 16 buildings under nominal conditions and three environmental stresses (darkness, smoke, and motion noise), where an embodied VLM explores unknown rooms, maps observed objects, and selects the safest gathering place. Open-weight models leave rooms unvisited in 95% of episodes and detect at most 51% of objects; closed-weight models explore more, though with an external memory (notepad), two of the three stop prematurely. Without external memory, most VLMs keep fewer of the objects they saw, especially in larger buildings. The start limits which rooms are explored, and open-weight models started in different rooms agree on the final room not significantly more often than chance. Moreover, these choices are biased by semantic priors: swapping a room's label is often enough to change the final choice. Finally, motion noise increases object position error (by 12-60% for closed-weight models), strong darkness lowers map recall by 28-31 percentage points, and dense smoke reduces seen objects by 25-39 points, while the choice among the rooms entered does not change significantly.

cs.AI · cs.MA · cs.RO

新论文 · v1arXiv:2611.22838

Better Rankers, Worse Retrievers: The Hidden Cost of RL Post-Training in Generative Recommendation

Yuheng Chen, Fan Zhang, Yixuan Xu, Chao Yang, Yang Xiang, Can Yang

原文摘要

Generative recommenders decode the semantic ID of a user's next item with a language model, and post-training them with reinforcement learning (RL) after supervised fine-tuning (SFT) has become standard practice. The gains are mostly reported on the first ten results, yet in deployment such models hand hundreds of candidates to a downstream ranker or reward model. We show that RL post-training has a hidden cost: it improves accuracy at the top of the list (hit@K for small K) but, on all five datasets we study, lowers the recall of the candidate list (hit@K for K in the hundreds). The model becomes a better ranker and a worse retriever. Controlled experiments trace the loss to the negative advantages that RL assigns to the candidates it samples, the rollout. The root cause is that only one next item is logged per user, so RL treats every other candidate as wrong. Yet these candidates are the model's most plausible alternatives, and often the next items of other users with similar histories. Penalising them pushes down exactly what similar users choose next, and these items drop out of those users' candidate lists. This diagnosis points directly to a remedy: out-of-rollout anchoring, a single additional loss term that preserves the SFT model's ordering of the items outside the rollout. It keeps the gain at the top and restores recall to the SFT level on all five datasets, and it is effective under other RL configurations as well. To our knowledge, this is the first systematic study of this recall loss: we measure it, identify its cause, and show that, once the cause is known, a simple remedy suffices.

cs.IR · cs.AI

新论文 · v1arXiv:2611.22837

Synergizing Evidence Retrieval and Utilization for Self-Improving Multimodal Scientific Document Reasoning

Frank Nie, Ethan B. Liu, Yuan Zhu, Jindong Han

原文摘要

Scientific document reasoning requires an agent to acquire and integrate evidence distributed across text, figures, and tables. Retrieval can identify relevant sources while missing complementary support, and answer-level feedback alone does not reveal whether an error stems from evidence acquisition or evidence use. We present an agentic Retriever--Perceiver--Reasoner framework for multimodal scientific document reasoning. The Retriever sequentially selects source-aligned evidence under a context budget. Given the selected evidence and question, the Perceiver constructs a question-conditioned latent ontology, an implicit organization of multimodal evidence in a shared continuous space. The Reasoner combines this latent guidance with the original sources to produce grounded answers. We train the three components through diagnostic-guided co-evolution: alternating updates optimize them with a shared answering reward, while Retrieval Potential Feedback (RPF) and Latent Efficacy Feedback (LEF) identify questions that need better retrieval or latent guidance and direct targeted resampling. Across four benchmarks and seven evaluation settings, our framework obtains average scores of 69.9 and 75.0 with 7B and 8B Reasoner backbones, exceeding the strongest baseline by 4.0 and 9.1 points, respectively.

cs.AI

新论文 · v1arXiv:2611.22826

OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making

Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski

原文摘要

Clinical care is a closed loop: clinicians observe partial evidence, infer the patient's state, and intervene, and each intervention determines what is observed next. This makes clinical decision making a partially observable Markov decision process (POMDP), in which a belief over a latent patient state must be updated from irregular, multimodal, and incomplete records. Yet most deep clinical models predict from a single snapshot or from coarsely aggregated history, while POMDP-based clinical methods need hand-specified discrete state spaces and transition models that real electronic health records cannot supply. We introduce OICycle (Observe, Infer, and Intervene Cycle), which learns a stochastic belief state directly from retrospective trajectories. At every episode, a learned recurrent operator fuses a sample of the previous belief with the new multimodal observations and the intervention that produced them. The resulting Gaussian belief is trained to predict clinicians' next interventions, the time to the next episode, and next-episode mortality. To enable reproducible evaluation, we release a benchmark derived from MIMIC-IV, MIMIC-IV-Note, and MIMIC-CXR that organizes 72,075 hospital admissions (5.4M laboratory, microbiology, radiology, prescription, and note records) into temporally ordered therapeutic--diagnostic episodes. Compared with an otherwise identical history-free model, OICycle improves next-intervention adaptive recall from 0.253 to 0.347, time-to-next-episode macro-F1 from 0.293 to 0.351, and next-episode mortality macro-F1 from 0.585 to 0.649. Analysis shows that the learned belief encodes intervention type and trajectory position and evolves smoothly across episodes, and that the benefit of history is concentrated in interventions whose ordering depends on prior findings.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22825

A tiny object detection dataset for high-altitude open-water search and rescue

Hui Xu, Chenfei Hou, Henglai Wei, Hao Wang, Yidong Jin, Xiulin Niu, Haoyang Zhang, Hui Zhang 等 9 位作者

原文摘要

Large aerial platforms often operate above 1.5 km to improve the efficiency of open water search and rescue (OW-SAR). However, long imaging distances, wide fields of view, and limited sensor resolution reduce objects to a few pixels, increasing their susceptibility to environmental interference and making detection harder than for conventional small objects. To our knowledge, existing datasets focus on low-altitude scenarios and do not support automatic detection at 1.5-2.0 km. We therefore present TinyWOD, a tiny object detection dataset for high-altitude OW-SAR using lifebuoys as detection targets. It comprises 11,359 manually annotated images and 19,505 annotated instances spanning diverse environments, lighting conditions, water colors, and surface ripples. Compared with existing datasets, TinyWOD contains much smaller objects and a substantially higher proportion of tiny instances; its average equivalent side length (ESL) is 12.7 pixels, with 76.96% of in stances having ESLs below 15 pixels, reflecting actual high-altitude water-rescue imaging conditions. We define APtiny, a tiny object detection metric, and benchmark mainstream and state-of-the-art networks using this and conventional metrics. All evaluated networks effectively detect tiny waterborne objects, demonstrating TinyWOD's reusability and utility. We expect this dataset to support research on tiny object detection in high-altitude OW-SAR.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.32619

Intuition Vectors from Pretrained Representations Steer Diffusion-Based Reasoning

Shahar Haim, Daniel C. McNamee

原文摘要

Abstract visual reasoning requires identifying relationships between few examples and applying them to novel inputs. Recent advances have been driven by large language and vision-language models or specialized domain-specific architectures. It remains unclear whether abstract reasoning can be supported directly by the relational geometry of pretrained visual representations, without relying on language-based inference or task-specific representation learning. We investigate this possibility using frozen self-supervised vision encoders. With latent vector arithmetic, we confirmed that the representational geometry of two self-supervised encoders support abstract concept discrimination on Bongard problems and encode systematic relationships between input-output pairs in ARC tasks. Simple vector differences between image embeddings, which we call intuition vectors, capture transformations that generalize across instances of the same task. These vectors distinguish among 794 abstract reasoning tasks with up to 87.2\% accuracy, preserve relational structure across task-invariant visual transformations, and guide output retrieval for unseen inputs. Given this, we tested the hypothesis that this relational structure can steer generative reasoning by conditioning a diffusion transformer operating in pretrained visual latent space. On held-out ARC tasks, intuition-vector conditioning outperforms conditioning on complete demonstrations while requiring nearly six times less test-time compute, and supports zero-shot inference. Taken together, our findings suggest that pretrained visual representations provide a transferable substrate for abstract reasoning, enabling a modular approach in which the relational structure inferred from demonstrations steer generative reasoning.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22812

Pluggable Subband-Decoupled Fusion and Unlabeled Capture Prototype Calibration: Bridging High-SNR Null-Subcarrier Regrowth and Low-SNR Coherent Preambles for Cross-Domain IoT RF Fingerprinting

Fengchong Yao, Jianbing Li, Qing Liu, Kefeng Song, Haitao Li, Song Wang, Kunpeng Wang

原文摘要

Zero-overhead physical-layer authentication at edge wireless access points (APs) is vital for securing resource-constrained Internet of Things (IoT) transceivers against credential cloning, yet cross-domain IEEE 802.11a/g radio frequency fingerprint identification (RFFI) faces an acute signal-to-noise ratio (SNR) crossover. Power-amplifier spectral regrowth on unpopulated null subcarriers resists indoor multipath at high SNR but decays quadratically below the thermal noise floor, whereas populated active in-band preambles survive low SNR yet degrade under severe multipath, causing static fusion to lose up to 44.7 percentage points (pp). To our knowledge, we propose the first RFFI framework that dynamically modulates active in-band waveforms and unpopulated null-subcarrier regrowth via a blind physical SNR gate: Pluggable Gated Subband-Decoupled Fusion with Unlabeled Capture-Aware Prototype Calibration (GSDF-CAPC). Avoiding the 20-35 dB subband gradient imbalance of joint training, GSDF pairs any frozen pretrained host backbone with a 46.3K null-subcarrier plug-in encoder (NS-Branch), fusing scale-standardized logits and gate-warped spherical embeddings under a source-calibrated lag-64 thermal-SNR gate with exact low-SNR fallback. Over unlabeled target AP captures, forward-only unbalanced optimal-transport calibration (UOT-CAPC) aligns shifted prototypes under packet-arrival skew and recovers parameter-free balanced Sinkhorn (U-CAPC) at equipartition. Across DataPort-WiFi, WiSig, and ORBIT MobRFFI, zero-retrain GSDF wins all 72/72 paired runs across eight backbones with 0.00 pp low-SNR loss, while edge IB-Host + GSDF (92.6K-93.3K active parameters, 1.82 ms single-core CPU latency) and timing-synchronized GSDF-STO / GSDF-Tri reach 57.50%-65.05% three-benchmark Macro-F1 (89.04%-100.00% over 5-10-packet IoT bursts).

cs.AI · cs.IT · eess.AS · eess.SP

版本更新 · v2arXiv:2610.34203

MatOS: An Agent Operating System for Materials Research

Dingyang Lyu, Jing Gao, Zhonghao Chang, Jingjie Huang, Xiangran Cheng, Xin He, Yongda Huang, Zhen Lei 等 17 位作者

原文摘要

Materials research relies on scattered and growing data, knowledge, and simulation tools, and a single study often spans multi-day workflows across literature analysis, computation, and experiment. Large language model agents can now retrieve materials data, operate simulation codes, and close design-synthesis-characterization loops with autonomous laboratories. However, extending these agents with new capabilities, keeping long-running tasks on track, and letting them learn from past tasks and user feedback remain difficult. Here we present MatOS, an agent operating system for materials research with three core components: (1) a layered scientific asset graph that organizes data, knowledge, tools, skills, roles, and workflows as reusable assets; (2) a stateful adaptive workflow that runs tasks as explicit execution graphs with scientific checks, so that they can be resumed and traced; and (3) evidence-driven asset evolution, which revises these assets from execution records and user feedback. On ResearchClawBench, MatOS improves on the previously best-performing agent by 11.15% with the same base model and extends the cost-score Pareto frontier. With a common base model, it outperforms Codex CLI and Claude Code, exceeding Codex CLI by 2.13% on MatTools and 4.17% on SciAgentGym. In eight research cases, MatOS narrowed more than 30 million candidate structures to 97 solid-electrolyte candidates, identified 89 halide variants with higher computed conductivity than their parent structures, linked the force errors of 11 pretrained interatomic potentials to local atomic environments, and supported two new methods that reduce errors by 3.1% and 13.6% relative to their baselines. These results show that organizing research capabilities as reusable, evolving assets enables agents to carry out long, multistage materials studies. Code is available at https://github.com/DingyangLyu/MatOS.

cs.AI · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.22790

NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding

Tianci Xie, Li Chen, Pinxue Guo, Rui Zheng

原文摘要

Fine-grained questions about long videos ask how many times an action occurs, in what order events unfold, or exactly when a state changes. Answering them can require finding brief moments scattered across hours of footage. Agentic models that decide when and where to look promise to find these moments, yet this ability is hard both to measure and to learn. Sparse supporting evidence may establish that an action occurred without establishing its total count; verifying timeline-wide claims requires checking for missed occurrences and double counting. Answer-only supervision, in turn, does not explicitly supervise the search for evidence. We present NexSight, which builds verifiable tasks to both evaluate and train agentic long-video understanding. Its agentic pipeline, SightForge, accepts a task only if a verifier blind to the draft answer can reconstruct it from evidence densely reacquired from the raw video and counterexample checks fail to refute it. This yields SightLine, 310 evidence-traceable tasks from 108 long videos, evaluated through SightLoop, a shared multiscale harness supporting temporal exploration, local inspection, evidence integration, and revisiting while recording returned observations. On disjoint videos, solver trajectories on verified tasks become step-level supervision for observation decisions. The strongest model reaches only 54.52% on SightLine, yet 79.35% when given the annotated evidence. With under 6K examples, Sight-35B nearly doubles its base model's interactive accuracy (21.29% to 42.26%), outperforms the 397B model of its family, begins using explicit spatial inspection after post-training, which its base model never uses, and gains over 8 points on two external long-video benchmarks.

cs.CV · cs.AI