跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 17:39 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 18:34 — 2026-11-08 18:34（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：2026-11-08 17:39最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 17:37（北京时间）
版本更新 · v2arXiv:2611.00815

VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training

Rui Zhang, Yujia Su, Ruixuan Li, Yuhua Li, Yixin Su

原文摘要

Open-source LLMs provide a flexible alternative to closed-source models for Text-to-SQL but still struggle with complex queries. Finetuning with chain-of-thought (CoT) data improves reasoning, yet standard datasets lack CoT annotations, requiring synthetic generation. Existing synthesis methods only verify the final answer, allowing flawed reasoning steps to corrupt the training data. We propose VCoT-SQL, a framework that improves Text-to-SQL generation through intermediate-step validated CoT supervision and a dedicated SQL validator, which enables small open-source models to outperform frontier closed-source models. VCoT-SQL trains two complementary models on curated reasoning traces: an SQL generator using clause-level CoT templates where reasoning steps are verified via execution and schema alignment checks, and an SQL validator using diagnostic CoT templates to detect syntactic, semantic, and type level errors. We further design a hierarchical schema filtering pipeline that integrates and refines complementary retrieval strategies to distill relevant database elements. VCoT-SQL achieves 66.82% execution accuracy on challenging dataset BIRD dev and 86.8% on Spider test, improving the base 7B model by 7% on BIRD. Notably, our CoT synthesis relies on 7B models yet outperforms methods that use 72B-scale or even proprietary closed source teachers for data generation, demonstrating that rigorous step-level validation can be more effective than scaling up teacher model size. Our dataset and code are available at https://github.com/INTREBID/VCoT-SQL.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06303

An Engineering Reading of the Bounded Halting Problem and Observable Properties of a Universal Machine

Sergey Salishev

原文摘要

The halting problem asks whether a program eventually halts, with unrestricted resources. Engineering systems instead certify bounded halting: given a program, an input, and a step budget T, decide whether the program halts within T steps. This paper studies two of its uses. First, it defines an exact finite-budget problem, placing the simulated program and the checker on the same unit-cost timescale, so the checker can be embedded in an adversarial program. A diagonal argument with explicit additive overhead shows that no fixed deterministic checker decides every instance within any fixed fraction of T below one, for large T. In the nondeterministic case, T bounds the branch depth allowed for a stable observable decision. Second, bounded-halting instances give adversarial tests for finitary universality, since a universal model must support arbitrary finite computations as T grows. The tests check resource growth with T, the absence of a fixed deliberation bound, and later access to intermediate data. They separate a fixed model with extendable external resources, a model family that grows with T, and a larger system built around a fixed component. For machine-learning systems, this identifies the resource growth a universality claim assumes and whether it fails for deployed models.

cs.CC · cs.AI · cs.FL · math.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06299

STEK: Structural-Terrain-Enhanced Koopman-Inspired Cross-Channel Regularization for Retrospective Battery Multi-Target Estimation

Jing Wang, Shiyuan Piao, Fugee Tsung

原文摘要

Retrospective battery characterization across heterogeneous cells is challenging because cycling records vary substantially with chemistry, protocol, cell format, capacity, and operating conditions. An endpoint charge--discharge curve captures the local condition of an evaluated cycle, while a cell-level lifecycle terrain summarizes structural evolution across the archived trajectory. We propose STEK, a structural-terrain-enhanced framework for retrospective battery multi-target estimation. STEK combines a cell-level lifecycle (dQ/dV) terrain with an endpoint-derived structural proxy through quality-proxy-conditioned gating. Bounded FiLM and a validity-gated residual head refine the endpoint-curve representation while preserving a curve-based prediction pathway. Battery-type and optional material-text representations further condition an identity-centered low-rank linear map, providing a Koopman-inspired cross-channel consistency objective without modeling temporal dynamics or performing rollout. Under the fixed seven-output MIX-battery protocol, the full retrospective setting improves aggregate performance over endpoint-only learned baselines across multiple temporal backbones; this comparison reflects both the additional archived context and the modeling design. Under matched auxiliary inputs, STEK outperforms direct concatenation and quality-unaware FiLM, while descriptor-removal tests show graceful fallback to the endpoint pathway. Deterministic rules remain preferable for directly recoverable capacity summaries. The method targets retrospective archive harmonization rather than online estimation from cycle t alone.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06296

Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning

Xi Chen, Julien Cumin, Fano Ramparany, Dominique Vaufreydaz

原文摘要

Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by the ontological mismatch of applying continuous physical motion models to discrete logical behaviors. To address these limitations, we propose a novel framework that reformulates data association as a sequential decision-making task within a Markov Decision Process (MDP). We solve the defined MDP via Behavior Cloning (BC) to avoid complex reward engineering by directly learning from expert demonstrations. We instantiate the policy using two complementary architectures, including a lightweight Transformer that treats association as a multi-label classification task over linearized event histories, and a fine-tuned Large Language Model (LLM) that reformulates the problem as conditional text generation to leverage pre-trained semantic knowledge. Extensive evaluations on three diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, particularly in resolving concurrent multi-resident events. Furthermore, the LLM-based policy shows preliminary cross-environment transfer potential under benchmark settings, while its robustness in real deployments still requires further validation.

cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06294

A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code

Jiongchi Yu, Keke Lian, Junqing Wang, Zhikang Fan, Zhaoxuan Li, Yongheng Huang, Ziming Zhao, Dong Zhang

原文摘要

Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's safeguards (e.g., authorization checks) or insecure code to imitate. However, context construction is designed almost exclusively for functional correctness, and secure-code benchmarks treat the context as fixed, so how repository context affects the security of generated code remains unclear. We construct CASE-Bench, a benchmark of 145 repository-level tasks from real CVEs in 51 projects. Each task runs in Docker, has functional tests and a proof-of-concept exploit validated in both directions, and is annotated with the repository code that enforces or undermines its security. Using CASE-Bench, we compare 13 context construction methods and six controls with six LLMs, edit single context elements, and analyze coding-agent trajectories. We find that (1) functionality-oriented context raises the functional pass rate by up to 8.2 percentage points (pp) but the secure pass rate by at most 3.7 pp, (2) withholding a safeguard lowers the secure pass rate by up to 8.1 pp, while one inserted insecure exemplar raises correct-but-exploitable code by 6.3 pp, and (3) coding agents observe the relevant safeguard in only 27-36% of trajectories. These findings inform security-aware context construction and secure-code evaluation.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.34249

Evolving Support Priorities in Empathetic Reinforcement Learning

Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen, Sirui Chen, Lewei Lu, Beier Zhu 等 9 位作者

原文摘要

We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve. Code is available at https://asa13opp.github.io/CARE-project-page.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06290

The Split Protocol Decides the Result: Re-Evaluating Encrypted Traffic Classification

Mayan Sharma, Kriti Saini, Devansh Behl

原文摘要

Encrypted traffic classifiers are routinely reported at 95-99% accuracy. We show that on one of two public corpora, the same model and code score macro-F1 0.992 under the evaluation protocol standard in the literature and 0.567 under a protocol that keeps flows from one packet capture on one side of the split. Nothing changes but the partition (gap 0.426 over eight seeds, p = 0.008 after Holm-Bonferroni correction). The inflation is not a property of random splitting as such. On a month of backbone QUIC traffic, we evaluate five split protocols at eight seeds each: random, temporal and client-disjoint splitting are statistically indistinguishable from session-disjoint, while server-disjoint splitting costs 0.192 macro-F1 (d = 17.0, p = 0.008). Which axis matters depends on how the corpus was collected, in a way invisible from its label space. We give a diagnostic that identifies the right axis before any model is trained: single-identifier probes. A decision tree on the capture identifier alone reaches 0.983 under a random split and exactly 0.000 under session-disjoint splitting. Under this evaluation, a metric-trained flow embedding leads four deep baselines but does not beat gradient-boosted trees on twenty packet sizes. Five of our own pre-registered architectural claims fail: distance-based rejection of unknown applications beats softmax thresholding, but ablating every metric objective makes rejection better, because class separation correlates at r = -0.88 with rejection quality. Few-shot enrollment is flat within a corpus but, across corpora, five labelled flows per class recover 91% of the deficit left by failed zero-shot transfer. All splits, results, code and negative findings are released.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06282

MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection

Kiet Dang Vu, Cao Le Minh Khoa, Nguyen Viet Tri Pham, An Nguyen Gia, Tam Le Thuc Ho, Duc Dung Nguyen

原文摘要

Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view. Recent transformer-based detectors learn geometry purely from image features and 3D box annotations, lacking the high-level semantic priors that vision-language models (VLMs) acquire from large-scale pretraining. VLMs offer such priors, but deploying one directly as a detector is impractical due to its heavy inference cost. We propose MonoLaDN, a language-guided denoising framework that transfers the geometric reasoning of a VLM into a monocular 3D detector while keeping the deployed model purely vision-based. During training, a frozen VLM produces structured reasoning about each object's occlusion, depth, dimension, and angle from the image and its ground-truth boxes. We encode this reasoning into queries, perturb them with noise, and train the detector to reconstruct the clean reasoning. Reconstructing the corrupted reasoning forces the detector's depth-guided features to internalize the VLM's geometric priors, so this knowledge remains available even after the reasoning path is discarded at inference, adding no latency or parameters to the deployed model. Experiments on KITTI 3D and nuScenes show that MonoLaDN consistently outperforms state-of-the-art detectors and generalizes well to new domains.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06280

DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation

Yizhou Zhang, Panqi Chen, Lei Cheng, Ting Zhang, Jianlong Li, Jianfeng Shi, Shikai Fang

原文摘要

Physics sensing in evolving environments requires reconstructing dense spatiotemporal fields from sparse observations while adapting where future observations should be collected. Existing reconstruction and sensor-placement methods have made substantial progress, but they typically rely on static sensing assumptions: they either use a single layout across all frames or optimize placements independently at each frame, which limits their ability to produce temporally coherent sensing trajectories. We introduce DyPSI, a dynamic physics sensing framework that formulates this problem as the joint generation of future fields and sensor trajectories conditioned on historical observations. DyPSI lifts discrete sensor coordinates into continuous Sensor Position Fields, encodes fields and sensing configurations with a shared Functional Tucker representation, and trains a joint diffusion model to generate future fields and sensing trajectories simultaneously in the resulting latent space. A Gaussian-process temporal kernel correlates the perturbation injected during diffusion training, biasing the denoiser toward temporally smooth recoveries, and we further provide an analysis linking the EDM training objective to a sequence-aggregated A-optimality criterion and a kernel-induced bound on discrete trajectory variation. Experiments on turbulent flow, GLORYS12 sea-surface temperature, and 3D car aerodynamics show that DyPSI consistently outperforms static and frame-wise placement strategies, with substantial error reduction under tight sensor budgets. The code is available at https://github.com/mengqi132/DyPSI.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06273

Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification

Dung Do Tien, Kien Nguyen Do Trung, Kiet Dang Vu, Trung Thai Tran, Duc Dung Nguyen

原文摘要

While recent feed-forward 3D Gaussian Splatting methods enable efficient driving-scene reconstruction from surround-view images, their reliance on a single observation fundamentally hinders novel-view synthesis. Regions occluded in the input can become visible from novel viewpoints, leaving the reconstructed Gaussians under-constrained and incomplete. Moving beyond image-space inpainting for rendered views, we introduce OccSplat, a feed-forward framework whose core contribution is Occlusion-Aware Gaussian Densification, explicitly targeting missing scene geometry rather than missing pixels. By predicting new Gaussian primitives for unsupported regions, OccSplat completes the scene directly in the 3D representation. Specifically, OccSplat first identifies occluded regions that lack Gaussian support through Gaussian Occlusion Mapping. Gaussian Occlusion Completion then generates new primitives for these regions. The predicted primitives are integrated into the original representation to improve novel-view synthesis while retaining feed-forward inference without per-scene optimization. Experiments on the nuScenes benchmark demonstrate that OccSplat improves on the compared methods and yields particularly large gains in occluded regions, leading to more accurate and visually coherent driving-scene reconstruction.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06270

NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation

Xinhao Lou, Dongye Xie, Peng Sun, Chenyi Zhuang, Kaicheng Yu, Tao Lin

原文摘要

Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the generator. We present NEXTGAN, which trains a scalar critic by regressing its input gradient onto displacements between independently paired reference and generated features at interpolated locations in frozen representation spaces. For a fixed generator, this regression is equivalent to an adversarial objective with a gradient-energy penalty, while the generator retains the standard potential-based GAN update. The same objective adapts pre-trained image and video generators with up to 14B parameters, without auxiliary losses, online teacher scores, or trajectories. On ImageNet $256 \times 256$, NEXTGAN achieves one-step FIDs of 2.87 with pixel-space JiT-B and 1.54 with latent-space DiT-XL/1; its adversarial form further reaches 1.36. For text-to-video generation, a single trained Wan2.1-1.3B model supports one-, two-, and four-step sampling, achieving the highest VBench total scores among the compared 1.3B methods at one and two steps. At two steps, NEXTGAN scores 83.13, exceeding rCM and AnyFlow by 1.25 and 0.47 points, respectively. Code is available at https://github.com/LINs-lab/NextGAN.git.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06265

Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature

Yun Young Choi, Asung Kil, Sun Woo Park, Minho Lee, Seokhwan Kim

原文摘要

Several widely used families of Graph Neural Networks carry a positive-definite geometric prior. Graph convolution read as heat diffusion needs a positive semi-definite operator, hyperbolic models place features on positive-definite Riemannian manifolds, and dot-product and GAT-style attention scores use positive-definite inner products. On heterophilic graphs, where edges often signify dissimilarity or structural repulsion, that prior is a mismatch: no positive-definite form can assign a negative squared distance to a direction the labels separate. To measure the mismatch, we introduce the Graph Signature Index ($s_{\mathcal{G}}$), the inertia of a class-compatibility matrix built from label topology alone, and we prove that no value of the edge or node homophily index in $(0,1)$ rules out a negative eigenvalue. We then propose the Pseudo-Riemannian Attention Network (PRAT), whose attention logit is a signed squared pseudo-distance under a learnable diagonal metric initialized from $s_{\mathcal{G}}$. The design is diagnose-then-learn: the signature supplies a sign structure that unconstrained training keeps outside near-zero directions, and the projection learns the rest of the metric around it. Across fifteen node-classification benchmarks PRAT outperforms or matches the strongest heterophily-adapted models. A controlled ablation ties that performance to the sign structure itself: with architecture and protocol fixed, forbidding the metric to be indefinite costs accuracy on the graphs $s_{\mathcal{G}}$ marks as indefinite and leaves the others unchanged.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06259

A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models

Dohyun Kim, Junyong Lhim, Kwanyong Park

原文摘要

People often make decisions by holistically reasoning over heterogeneous forms of personal information. In this paper, we study the relatively underexplored capability of multimodal personalized reasoning in multimodal large language models (MLLMs). To this end, we introduce \texttt{MPRBench}, a novel and comprehensive benchmark specifically designed to evaluate personalized reasoning across a wide range of tasks and real-world challenges. \texttt{MPRBench} consists of 12 sub-tasks and additionally supports interpretable analysis of representative error cases. Through extensive experiments, we find that current personalized MLLMs still struggle with personalized reasoning due to several key challenges, including inaccurate recognition of personalized concepts and sensitivity to irrelevant personal information. We hope that MPRBench will stimulate further research on personalized reasoning in MLLMs. Code and data are available at https://github.com/kkdh15/MPRBench

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06254

HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents

Zhi Hong, Qianlong Wang, Hongchen Wei, Aidan Wu, Daohong Ying, Mingze Kong, Bei Liu, Chong Luo

原文摘要

The performance of large language model (LLM) agents depends on both the underlying model and the harness that governs interaction with tools and the environment. Yet harness design remains largely manual, and automating it requires navigating an open-ended search space through costly end-to-end evaluations. We introduce HarnessFlow, a framework for optimizing complete executable harnesses under a limited candidate-evaluation budget, with the model and task environment held fixed. HarnessFlow organizes candidates and their evaluation histories in a refinement tree, using a Monte Carlo Tree Search (MCTS)-based policy to balance exploitation and exploration. A coding agent refines selected harnesses using archived code, execution feedback, and a library of reusable harness mechanisms. With 15 refinement attempts per benchmark, HarnessFlow achieves the highest mean test scores among the compared methods on six benchmarks spanning agentic tasks, coding, and web interaction. The optimized harnesses achieve an average score of 69.48%, outperforming the initial harnesses and Meta-Harness by 10.89 and 3.95 percentage points, respectively, while incurring lower average per-task execution costs than hand-engineered baselines. These results suggest that structured harness search offers a promising route toward automating the design of capable and efficient LLM agents.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10402

Every finite group admits a just finite presentation

Marc Lackenby

原文摘要

A finite presentation < X | R > of a finite group is called `just finite' if removing any relation from R results in a presentation for an infinite group. It has been an open question (Kourovka Notebook, Problem 21.10) whether every finite group admits such a presentation. We resolve this conjecture in the affirmative.

math.GR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16857

Learning to Learn from Multimodal Experience

Xingyu Sui, Weixiang Zhao, Yongxin Tang, Yanyan Zhao, Yang Wu, Dandan Tu, Bing Qin

原文摘要

Multimodal agents increasingly interact with real-world-like environments and generate rich trajectories spanning perception, reasoning, and action. A key research focus is how to transform these raw multimodal trajectories into reusable experience that can improve future task performance. Existing experience-driven learning methods are mostly developed in textual settings and typically rely on manually designed memory schemas, making them less effective for multimodal experience that requires composing heterogeneous signals across modalities, temporal scales, and abstraction levels. We propose AutoMMemo, a general framework that enables agents to automatically design memory mechanisms for learning from multimodal experience. AutoMMemo represents each memory mechanism as an executable memo program, which defines how past episodes are stored, organized, and retrieved. It discovers effective memo programs through an iterative process of update-then-retrieve evaluation, reflection-guided mutation, and budget-aware tree search. Experiments across GUI/Web navigation and multimodal visual reasoning benchmarks show that AutoMMemo consistently improves agent performance over no-memory agents and fixed memory baselines, while maintaining reasonable token and interaction costs. Transfer and search-process analyses further demonstrate that the learned memory designs capture reusable experience structures and progressively refine retrieval relevance. These results highlight adaptive memory design as a key optimization target for multimodal experience-driven learning. Code is available at https://github.com/XingYuSSS/AutoMMemo.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06244

Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains

Sumeet Ramesh Motwani, Tejas Krishnan, Alistair Letcher, Charles London, Suhaas Bhat, Huitian Jiao, Philip Torr, Riashat Islam 等 13 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation. Extending these gains to open-ended domains remains challenging: ground-truth verification is unavailable, human annotation is expensive, and learned reward models are prone to reward hacking. The generation-verification gap, where judging good outputs is easier than producing them, offers a potential path to improvement. However, rubric-based judges are often imprecise and stationary, so policies can overfit or reward hack them. We introduce Rubric Curriculum RL (RcRL), which exploits this gap without new data, human annotations, or stronger teacher models. We combine pairwise preferences over rollouts with a curriculum over rubric criteria, yielding a more discriminative signal than absolute scoring and a non-stationary objective. Whereas baselines plateau within a few hundred steps, RcRL preserves output entropy and keeps improving past 1000 steps. On creative writing, RcRL achieves a 70.5% human win rate against the base model, with gains across benchmarks and judges. On HealthBench, RcRL improves over the base model by 14.6% (full set) and 25.4% (consensus subset), outperforming all training baselines, including instance-specific rubrics.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06219

A Definition of Catastrophic Performance

Henrik Marklund, Alex Infanger, Benjamin Van Roy

原文摘要

A central challenge in AI is specifying objectives that align with human preferences. While existing theoretical results elucidate how misspecification impacts performance, they typically do not distinguish between merely suboptimal and catastrophic outcomes. To enable rigorous analysis of catastrophic risk from AI misalignment, we introduce a formal definition of catastrophic performance. Our definition is based on two reference values. The first, baseline value, captures the value attained if no agent is deployed. The second, orthogonal value, captures the value of a trajectory that is unrelated to human preferences, in a sense we describe. Orthogonal value is typically far worse than baseline value. We interpret these reference values through examples in which past human activity has altered the state of the environment to human benefit. Starting at the resulting state, an AI agent is deployed with the goal of accelerating further progress. Catastrophic performance represents this agent's undoing of benefits afforded by human activity.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.10127

Population-Aligned Persona Generation for LLM-based Social Simulation

Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Max Xiong, Tianfu Wang, Teng Xiao, Yuxuan Lei, Fengqing Jiang 等 13 位作者

原文摘要

Recent advances in large language models (LLMs) have enabled large-scale, high-fidelity social simulations, creating new opportunities for computational social science. However, constructing persona sets that faithfully reflect real-world population diversity remains a key challenge. Existing studies often emphasize agentic frameworks and simulation environments, while paying less attention to persona generation and the biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06204

CoSafe: Cooperative Runtime Safety Assurance for Mixed-Traffic Autonomous Driving

Dingji Wang, You Lu, Haowen Jiang, Yanggang Chen, Yuyang Bi, Bihuan Chen, Shenglin Bao, Xin Peng

原文摘要

With the rapid development of autonomous driving systems (ADSes), real-world roads are evolving into mixed-traffic environments where autonomous vehicles (AVs) and other traffic participants (e.g., human-driven vehicles (HDVs), cyclists, and pedestrians) coexist and interact with each other. However, current ADSes still incur various safety violations in mixed traffic scenarios, raising a strong demand for runtime safety assurance frameworks that can continuously monitor hazards and prevent potential violations. Existing ego-centric assurance approaches are insufficient for mixed traffic, where violations often arise from locally reasonable yet jointly incompatible decisions among multiple vehicles and cannot be reliably resolved through independent takeover. To bridge this gap, we propose CoSafe, a modular and ADS-agnostic cooperative runtime safety assurance framework for mixed-traffic autonomous driving to extend runtime safety assurance from ego-centric takeover to scene-level cooperative intervention. CoSafe leverages vehicle-to-everything (V2X) communication to enable roadside units (RSUs) to monitor scene-level hazards and jointly mitigate hazards involving multiple vehicles. We integrate CoSafe with seven state-of-the-art ADSes, and our evaluation on the InterDrive benchmark demonstrates that CoSafe improves the driving score of AVs by 70.03% on average, reduces safety violations by 87.80%, and accurately identifies unsafe AVs with an F3 score of 0.930, while satisfying real-time constraints.

cs.SE · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06185

Editing Large Language Models with Geometry-Aware Regularization

Bingqing Liu, Wei Liu, Jun Wang, Xiaobo Sun, Yuhua Li, Ruixuan Li

原文摘要

Knowledge editing has become a key technique for updating knowledge in large language models. However, existing methods neglect the geometric structure of the knowledge representation space, leading to two key limitations: they cannot distinguish which pre-trained knowledge should be preferentially preserved (core vs. non-core) nor which new edits are inherently difficult (hard vs. easy). To address this, we propose GEdit, a geometry-aware framework built on a Low-Rank Plus Diagonal (LR+D) factor model that captures the intrinsic low-rank structure of Transformer FFN hidden representations. GEdit features two complementary mechanisms. First, the low-rank regularization applies targeted protection on a low-rank core knowledge subspace. Second, the adaptive regularization dynamically adjusts the regularization strength based on each edit request's editability: relaxing constraints for hard edits to ensure success, and tightening them for easy edits to better preserve pretrained knowledge. Extensive experiments on GPT2-XL, GPT-J, and LLaMA-3-8B under large-scale editing scenarios, including both mini-batch and fully sequential editing settings with up to 10,000 continuous updates, show that GEdit consistently and significantly outperforms state-of-the-art baselines in both editing success and knowledge preservation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06170

AssameseLM-E2B: An Open-Weight Assamese Language Model for Efficient Consumer-Grade Deployment

Pragyan Phukan

原文摘要

While Large Language Models (LLMs) excel in high-resource languages, their performance often degrades in low-resource languages due to tokenization inefficiencies, generative instability, and linguistic interference. This paper presents AssameseLM-E2B and its instruction-tuned variant, AssameseLM-E2B-it, a 2-billion-parameter model adapted specifically for low resource Assamese language. Built upon the Gemma-4 architecture, the model incorporates an expanded byte-level BPE vocabulary to reduce tokenization overhead by nearly 500% compared with multilingual 2B--3B baselines. We employ a parameter-efficient Continual Pre-Training (CPT) pipeline with Hybrid LoRA, followed by Supervised Fine-Tuning (SFT) on a balanced, multi-domain dataset to enhance instruction-following and Retrieval-Augmented Generation (RAG) capabilities. Evaluation demonstrates a Bits-per-Byte (BPB) score of 0.7488 on FLORES-200, alongside an overall RAG score of 96.7% and 100% refusal accuracy on adversarial unanswerable prompts. Comparative analysis reveals significant limitations in general-purpose baselines, including receptive-productive decoupling, generative degradation on Romanized Assamese, and unintended Bengali script assimilation. These results demonstrate the potential of parameter-efficient adaptation for developing capable, locally deployable language models for low-resource languages under constrained computational resources.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06168

Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models

Xinghao Li, Chenchen Tan, Youyang Qu, Shujie Cui, Xingliang Yuan, Cunjian Chen, Chi Liu, Longxiang Gao

原文摘要

Multimodal large reasoning models (MLRMs) integrate visual inputs with textual and parametric knowledge, allowing sensitive information to be accessed through cross-modal associations during reasoning. This raises privacy concerns when a visual input should no longer provide access to such information. Machine unlearning can remove this influence without retraining the model from scratch. However, multimodal unlearning methods mainly target samples, concepts, or knowledge content, without separating the knowledge from the cross-modal association through which it is accessed. In reasoning models, target information may disappear from the final answer while remaining in intermediate reasoning, or be replaced by incorrect substitute knowledge. We therefore study cross-modal association unlearning, where the forget target is a designated visual-to-knowledge association: the model should suppress target-bearing behavior under the designated visual context while preserving access to the same knowledge in permitted contexts. We propose Visual-Keyed Counterfactual Rebinding (VKCR), a parameter-efficient framework for cross-modal association editing. VKCR first localizes the edit to a compact association-conditioned parameter subspace. It then reduces support for the designated target at task outputs and counterfactually rebinds the affected reasoning behavior by discouraging target-bearing or unsupported continuations while favoring valid non-sensitive alternatives. We further introduce CLEAR-R and MLLMU-R to evaluate target leakage, hallucinated reassociation, reasoning preservation, and modality-specific utility. Experiments show that VKCR substantially reduces image-conditioned target leakage and hallucinated reassociation, including across heterogeneous task formulations, while preserving non-sensitive visual reasoning and permitted text-only knowledge.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.10805

Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation

Amit Aflalo, Shahaf E. Finder, Roy Amoyal, Eran Treister, Oren Freifeld

原文摘要

Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field exponentially with the number of decomposition levels while keeping the parameter count linear. However, its reference implementation is severely memory-bound due to excessive data movement through high-bandwidth memory (HBM). We develop an I/O model of WTConv to characterize this bottleneck and use it to guide three algebraic reformulations: (1) recomputing the inexpensive Haar analysis butterfly on chip, (2) collapsing the multi-level synthesis cascade into a single closed-form pass indexed by output-coordinate bits, and (3) folding learned per-channel scales into the convolution weights. Together, these reformulations enable an I/O-aware fused implementation that substantially reduces HBM traffic. We evaluate the WTConvNeXt configuration across decomposition levels and a broad range of tensor shapes. Despite performing comparable arithmetic, the reference WTConv is substantially slower than the depthwise convolution it replaces. Our reformulation reduces modeled HBM traffic by approximately $2.55\times$, yielding up to a $4.35\times$ training speedup over the reference while roughly halving peak memory usage. Thus, our reformulation preserves the benefits of WTConv while substantially reducing its execution time and memory footprint, removing the systems overhead that previously limited its practical efficiency.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2308.06717

When the Agent Learns Too: Learning to Incentivize with Unobserved Rewards

Ilgin Dogan, Zuo-Jun Max Shen, Anil Aswani

原文摘要

In practice, incentive providers (i.e., principals) often cannot observe the reward realizations of incentivized agents, which is in contrast to many principal-agent models that have been previously studied. This information asymmetry challenges the principal to consistently estimate the agent's unknown rewards by solely watching the agent's decisions, which becomes even more challenging when the agent has to learn its own rewards. This complex setting is observed in various real-life scenarios ranging from renewable energy storage contracts to personalized healthcare incentives. Hence, it offers not only interesting theoretical questions but also wide practical relevance. This paper explores a repeated adverse selection game between a self-interested learning agent and a learning principal. The agent tackles a multi-armed bandit (MAB) problem to maximize their expected reward plus incentive. On top of the agent's learning, the principal trains a parallel algorithm and faces a trade-off between consistently estimating the agent's unknown rewards and maximizing their own utility by offering adaptive incentives to lead the agent. For a non-parametric model, we introduce an estimator whose only input is the history of principal's incentives and agent's choices. We unite this estimator with a proposed data-driven incentive policy within a MAB framework. Without restricting the type of the agent's algorithm, we prove finite-sample consistency of the estimator and a rigorous regret bound for the principal by considering the sequential externality imposed by the agent. Lastly, our theoretical results are reinforced by simulations justifying applicability of our framework to green energy aggregator contracts.

cs.LG · cs.AI · cs.GT · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.14697

Evolutionary System Prompt Learning for Reinforcement Learning in LLMs

Lunjun Zhang, Ryan Chen, Bradly C. Stadie

原文摘要

Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving a model's experiential context and its weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel, then uses them to jointly update the weights with RL and evolve the system prompts with self-reflection. E-SPL encourages a natural division between procedural knowledge in weights and interpretable declarative knowledge in system prompts. Most notably, in an easy-to-hard generalization setting (AIME $\rightarrow$ BeyondAIME), E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1%. E-SPL also improves RL on AIME 2025 (56.3% $\rightarrow$ 60.6%), HMMT 2025 (50.0% $\rightarrow$ 52.7%), and agentic search (44.2% $\rightarrow$ 48.6% on gpt-oss-120b). Across all settings, E-SPL outperforms both RL-only and evolution-only baselines, demonstrating that weight updates and context updates are deeply synergistic and can together yield gains in generalization that neither achieves alone. Code is available at https://github.com/LunjunZhang/E-SPL.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06151

CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution

Guangtao Zhang, Haonan Wu, Junxuan Gao, Zhengyang Liu, Zhaoxi Zeng, Zhihao Li, Jianguo Huang, Zhiqiang Liu

原文摘要

Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose $\textit{CARM}$ (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most $α$ at an $O(1/T)$ rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-$\textit{a}$ SR stream, CARM reduces the empirical violation rate from $43.49\%$ to $9.38\%$ and the moving-average exceedance frequency from $47.29\%$ to $1.22\%$ at $α=0.10$, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.

cs.AI · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06147

SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving

Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi, Arya Fayyazi, Souvik Kundu, Mehdi Kamal, Massoud Pedram

原文摘要

Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by running even fewer experts per token, and they are validated on accuracy benchmarks. We show that these methods can weaken the model's refusal of harmful requests, and we introduce SafeStart, which largely restores refusal while keeping most of the speedup. In vLLM on one RTX A6000, keeping about two thirds of the selected experts speeds up offline decoding by 15 to 28% at batch size 8. We find that, at this setting, under a jailbreak that tells the model not to refuse, the share of harmful requests that the model answers rises by 18.4 percentage points on Qwen1.5-MoE, 9.5 on OLMoE, and 6.6 on DeepSeek-V2-Lite, the three of nine models where it rises significantly, while MMLU accuracy drops by less than two points. We discover that most of this increase arises while the model processes the prompt and generates its first few tokens. SafeStart therefore runs all experts for the prompt and the first eight generated tokens, and the reduced set of experts afterwards, through a fused kernel in vLLM. With experts removed, SafeStart keeps at least 85% of the offline decode speedup at batch sizes 8 and 32 and brings the change under this jailbreak to between -2.1 and +1.3 points for three expert-reduction methods on these three models. On 889 held-out requests, in an analysis fixed before generation, truncation raises harmful compliance by 5.8 to 21.4 points, and SafeStart leaves a rise of 0.6 to 2.6 points, non-inferior to the original model on two of the three models. Our results show that faster MoE serving need not cost safety: a serving system can keep most of the gain from running fewer experts by running all of them at the start of each response, and it should test refusal, not only accuracy, before it enables such a method.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06962

Formalizing inverse problems in the age of AI: possibilities, pitfalls, and an invitation

Christian Clason, Tapio Helin, Medet Nursultanov, Lauri Oksanen

原文摘要

Proof assistants such as Lean check mathematical proofs down to the axioms, and AI agents have recently made writing such proofs cheap. We describe AutoIP, a Lean library in which classical linear regularization theory, together with the functional analysis it rests on, has been autoformalized by AI agents. A machine-checked proof certifies only the formal statement it proves, so the remaining human task is to confirm that each formal statement says what was intended. We organize the library around this task: a reviewer compares the formal statements with their natural-language counterparts and never needs to read a proof. Our experience is that the risks lie in the statements rather than in the proofs, and that simple automated tests on the statements can expose problems even in the established literature. We illustrate this with a textbook theorem whose hypothesis is more restrictive than asserted. We invite the inverse problems community to extend and build on the library.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2304.07407

Learning to Incentivize Perfect-Knowledge Agents with Unobserved Rewards

Ilgin Dogan, Zuo-Jun Max Shen, Anil Aswani

原文摘要

Motivated by a number of real-world applications from domains like healthcare and sustainable transportation, in this paper we study a scenario of repeated principal-agent games within a multi-armed bandit (MAB) framework, where: the principal gives a different incentive for each bandit arm, the agent picks a bandit arm to maximize its own expected reward plus incentive, and the principal observes which arm is chosen and receives a reward (different than that of the agent) for the chosen arm. Designing policies for the principal is challenging because the principal cannot directly observe the reward that the agent receives for their chosen actions, and so the principal cannot directly learn the expected reward using existing estimation techniques. As a result, the problem of designing policies for this scenario, as well as similar ones, remains mostly unexplored. In this paper, we construct a policy that achieves a low regret (i.e., square-root regret up to a log factor) in this scenario for the case where the agent has perfect-knowledge about its own expected rewards for each bandit arm. We design our policy by first constructing an estimator for the agent's expected reward for each bandit arm. Since our estimator uses as data the sequence of incentives offered and subsequently chosen arms, the principal's estimation can be regarded as an analogy of online inverse optimization in MAB's. Next, we construct a policy that we prove achieves a low regret by deriving finite-sample concentration bounds for our estimator. We conclude with numerical simulations demonstrating the applicability of our framework to personalized adherence-improving incentive design for long-term statin treatments.

cs.LG · cs.AI · cs.GT · stat.ML

查看论文
arXiv ↗PDF ↗