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：2026-11-09 03:03 · 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 2026-11-08 04:04 — 2026-11-09 04:04（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：2026-11-09 03:03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 2026-11-09 03:01（北京时间）
版本更新 · v3arXiv:2610.11213

AliO: Output Alignment Matters in Long-Term Time Series Forecasing

Kwangryeol Park, Jaeho Kim, Seulki Lee

原文摘要

Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasingly crucial in real-world applications such as weather forecasting and planning of electricity consumption. However, state-of-the-art LTSF models often fail to achieve prediction output alignment for the same timestamps across lagged input sequences. Instead, these models exhibit low output alignment, resulting in fluctuation in prediction outputs for the same timestamps, undermining the model's reliability. To address this, we propose AliO (Align Outputs), a novel approach designed to improve the output alignment of LTSF models by reducing the discrepancies between prediction outputs for the same timestamps in both the time and frequency domains. To measure output alignment, we introduce a new metric, TAM (Time Alignment Metric), which quantifies the alignment between prediction outputs, whereas existing metrics such as MSE only capture the distance between prediction outputs and ground truths. Experimental results show that AliO effectively improves the output alignment, i.e., up to 58.2% in TAM, while maintaining or enhancing the forecasting performance (up to 27.5%). This improved output alignment increases the reliability of the LTSF models, making them more applicable in real-world scenarios.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02561

EEFA: A Framework for the Ethical Evaluation of AI Agents

Swathi Pallikala, Yashas Hariprasad

原文摘要

The rapid deployment of autonomous AI agents across consequential domains including healthcare, legal services, nancial management, and enterprise workows has created an urgent governance challenge. While the eld of AI evaluation has produced sophisticated benchmarks for measuring agent capability, these frameworks measure exclusively what agents can do rather than how they do it. The ethical dimensions most critical to responsible agent deployment, in- cluding respect for human autonomy, harm avoidance, transparency and non-deception, privacy compliance, and accountability, are systematically absent from current evaluation practice. This paper addresses that gap through three contributions. First, a structured literature review of twelve leading AI agent benchmarks characterizes the ethical dimensions those bench- marks do and do not measure. Second, the Ethical Evaluation Framework for AI Agents (EEFA) is introduced as a comprehensive, operationalizable instrument for ethical agent evaluation, grounded in established AI ethics principles and designed for use by developers, auditors, and regulators. Third, a reproducible validation protocol is specied for applying the EEFA to deployed agent systems, with illustrative test scenarios across all ve framework dimensions. The EEFA is organized across ve primary dimensions: Autonomy Preservation, Harm Avoid- ance, Transparency and Non-Deception, Privacy Compliance, and Accountability and Traceabil- ity. The framework maps directly onto the requirements of the EU AI Act and the NIST AI Risk Management Framework, positioning it as a practical compliance assessment instrument for high-risk AI applications. Empirical application of the framework across diverse benchmarks and agent systems is identied as a priority direction for future work.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02555

Sequential Recovery Updates for Learned Controllers under Successful-Trajectory Preservation

Zongtan Li, Tianming Liu, Ye Zhao

原文摘要

A competent learned controller already recovers from many disturbances. Improving it means learning a correction, and learning when not to apply it. Freezing a skill's parameters does not settle the second half. In a controller that routes among frozen skills, a new entry rule can redirect the states an old skill succeeded on. We therefore constrain entry instead of parameters. Each update searches for a feedback skill at a measured failure. It fits an entry rule that reads observations and rejects every state on an accumulated successful trajectory. The skill is admitted only if the composed controller reproduces the new recovery on its own and replays every protected trajectory exactly. A finite-trajectory condition states when this preserves the previous controller. One mechanism runs on four streams: two motions on each of two humanoid systems. Two updates per stream add 62 recoveries over 192 withheld perturbations, and lose none of the base controller's successes. We then price that guarantee. Removing the constraint recovers 33 more conditions but stops eight protected ones from completing at all, and excluding only what admission proves necessary recovers none of that cost.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06258

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks

Taehun Cha, Daniel Beaglehole, Adityanarayanan Radhakrishnan, Donghun Lee

原文摘要

Understanding how deep neural networks learn representations remains a central challenge in machine learning theory. In this work, we propose a feature-centric framework for analyzing neural network training by relating weight updates to feature evolution. We introduce a simple identity, the Feature Learning Equation, which identifies the weight Gram matrix as the key object capturing feature dynamics. This enables us to interpret gradient descent as implicitly inducing a hypothetical evolution of features, whose covariance structure, termed the Virtual Covariance, characterizes how representations evolve during training. Building on this perspective, we introduce Target Linearity, a measure quantifying the linear alignment between features and targets. By analyzing the training and layer-wise dynamics, we show that deep networks learn to sequentially transform representations toward target-linear structure. This linearization perspective provides a unified interpretation of several empirical phenomena, including Neural Collapse and linear interpolation in generative models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.14594

SynBench: A Benchmark for Differentially Private Text Generation

Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Iqra Zahid, Yuping Wu, Yulong Wu, Hao Li, Jie Zhang 等 12 位作者

原文摘要

Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of re-identification and membership inference. LLM-based methods deliver promising results; however, comparisons are exacerbated by differing evaluation setups and "private" datasets, potential pre-training contamination is not considered and guarantees are not verified with DP audits. To advance this field, we introduce a unified evaluation framework with standardised utility and fidelity metrics and privacy audits, encompassing nine curated datasets that capture domain-specific complexities such as technical jargon, long-context dependencies, and specialised document structures. In a large-scale empirical study, we benchmark LLM-based state-of-the-art DP text generators of varying sizes (between 1--8B). Our results indicate that DP synthetic text generation remains an unsolved challenge, with quality deteriorating more as the private datasets deviate further from the generators' pre-training corpora. Our analyses suggest that synthetic data quality may be overestimated when LLMs have been pre-trained---without DP---on portions of the "private" data to be generated, and our membership inference (MIA) auditing setup for synthetic text reveals measurable membership signals even under tight privacy budgets. Finally, we note that under the "public pre-training, private generation" paradigm, the nominal $(\varepsilon,δ)$ guarantee does not account for exposure during pre-training, motivating contamination-aware evaluation of DP synthetic text generation. Code and data splits: https://github.com/ImperialGlobalSingapore/synbench

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02539

Scientific Liquidity Agents: An Agent-Based Model of Knowledge Arbitrage in Scientific Communities

Koutian Wu, You Liu, Yue Liu, Zhiping Li, Ergan Shang

原文摘要

Scientific knowledge gains new uses when ideas, methods, and results move between research contexts. Understanding this process requires a model of both specialized knowledge production and the intermediary activities that connect it. We introduce Scientific Liquidity Agents (SLA), an agent-based model of knowledge arbitrage in scientific communities. SLA represents domain specialists and epistemic arbitrageurs within a shared environment of research problems, researcher interactions, and scientific artifacts. Individual decisions connect to collective state through a belief-desire-intention architecture, a prerequisite-based problem graph, a dynamic interaction network, and a persistent publication registry. The framework makes researcher roles and knowledge-transfer frictions explicit, providing a process-oriented account of scientific production and exchange. Two exploratory simulations with 10 and 18 agents produce 68 and 274 registered papers. In the smaller run, arbitrageurs take part in 16 of the 26 contact pairs that join this community into one connected component, while topical similarity alone splits it into seven. The same run yields three similarity edges, 26 contact pairs, and two coauthorship pairs, so measured community structure depends on what counts as a link. Paper production is abundant, but no recorded replication succeeds, which places the bottleneck in verification rather than production. Solved-problem sets correspond to the prerequisite reachability of the disciplines represented in each community. SLA makes knowledge liquidity, the movement and reuse of artifacts across domains, a quantity that agentic science can simulate and measure.

cs.MA · cs.AI · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02536

FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly

Fuqiang Wang, Jiahao Fu, Ren Hefeng, Yining Qian, Chuanting Zhang, Cheng Tan, Yuwen Liu, Jingxuan Wei

原文摘要

Large language models have demonstrated strong capabilities in structured reasoning and code generation, yet identifying an assembly fault does not guarantee the ability to generate executable rework programs. In interlocking assemblies, a locally plausible repair program may violate blocking dependencies, omit required recovery operations, or terminate in an incorrect configuration. We identify this challenge as fault-conditioned executable rework generation, where models must jointly reason about structural failures and generate programs that restore constrained assembly states. To benchmark this capability, we introduce FORGE-Bench, containing 4,000 tasks across 26 interlocking assemblies with five assemblies held out for evaluating generalization to unseen structures. We further propose FORGE (Fault-Oriented Rework Code Generation for Executable Interlocking Assembly), a structured state-to-program framework that decomposes rework generation into Rework Structuring and Action Grounding. Rework Structuring captures fault-induced recovery dependencies, while Action Grounding maps these dependencies into state-conditioned executable actions. Experiments show that locally reasonable repair code is insufficient for reliable assembly recovery, and that connecting structural recovery reasoning with executable action realization is essential for verified target restoration.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07138

Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents

Deeraj S K, Sadhana Devarajan, Krishna Mehra, Sudhakar Mishra

原文摘要

Reinforcement learning from verifiable emotion rewards (RLVER) yields strong empathetic language models, but is evaluated with cooperative, honest simulated users. Real users gaslight, escalate, and demand unconditional validation. We introduce the Adversarial Empathy Benchmark (AEB), six adversarial trajectory types whose discriminative rewards penalize formulaic comfort, and the Emotional Consistency Score (ECS), which separates whether a model \emph{improves} the user's emotional state from whether that state stays legible in the transcript. Across eight scenario-matched conditions (480 dialogues; two RLVER and two Qwen2.5 base models, with and without thinking), RLVER-PPO-Think outperforms its untuned same-scale baseline (FS $0.979$ vs.\ $0.761$, $p<10^{-12}$) with no dialogue collapses and 53\% higher hidden-intention detection; the gain is not explained by response length. Yet under an independent cross-family judge (Gemma-3-4b-it), ECS is indistinguishable between the two ($p=0.43$). We call this an outcome--legibility dissociation: RLVER improves emotional outcomes without making the user's state more legible. We do not claim ECS measures internal understanding.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02516

Cumulative and Audited Guardrail Tool Evolution for LLM Agent Safety

Xiao Yang, Aishan Liu, Siyuan Liang, Zonghao Ying, Le Wang, Jiakai Wang, Xianglong Liu, Dacheng Tao

原文摘要

Large language model (LLM) agents increasingly operate in open-world environments where safety risks cannot be fully predefined. However, most existing guardrail mechanisms remain static, relying on fixed rules, prompts, or classifiers that generalize poorly to emerging risks. Here we present EVOLVE, a tool-level self-evolving defense framework that formulates agent security as a process of cumulative security evolution. Inspired by how human societies transform experiences into transferable protective knowledge, EVOLVE externalizes security knowledge into executable guardrail tools that are continuously inherited, independently audited, and iteratively refined through lifelong interaction. Across multiple benchmarks, backbone models, and embodied environments, EVOLVE consistently outperforms existing defenses across diverse risk scenarios with +22\% average F1 score. We further validate the framework in real-world robotic and autonomous agent systems. Our results suggest that scalable agent safety may require continuously evolving defense systems rather than static guardrails.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02512

Latent Spectral Prompting for Multimodal Hyperspectral Object Tracking

Wangshu Cai, Jun Zhou, Lei Wang, Mohammad Aminul Islam, Xu Han, Kuldip Paliwal

原文摘要

Hyperspectral videos provide rich spectral signatures for robust tracking under challenging conditions such as camouflage and low illumination. However, limited hyperspectral annotations and the large RGB-hyperspectral domain gap hinder the direct use of modern temporally pretrained RGB trackers. We propose SProTrack, a multimodal framework that transfers temporal knowledge from pretrained RGB trackers to the hyperspectral domain through latent spectral prompting. The key idea is to decouple temporal modeling from spectral adaptation, allowing temporal dynamics to be inherited from RGB foundation models while hyperspectral information is learned from unlabeled data in a self-supervised manner. Unlike band-selection methods that discard most spectral information or prompt-based approaches that rely on local-search crops, SProTrack learns a global, scene-level spectral representation from the full hyperspectral frame using an autoencoder. This latent representation is used to guide spectral prompt extraction while a pretrained RGB tracker preserves strong temporal modeling on RGB-compatible inputs. By encoding spectral-spatial structure into compact latent prompts, SProTrack bridges the RGB-hyperspectral modality gap without extensive retraining or dense supervision. Experiments on HOT2020 and HOT2023 demonstrate that SProTrack achieves the best overall performance, with strong results across all spectral domains.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02511

When Prediction Shapes the Future: A BlueSky Agenda for Reflexive Time Series Analysis

Tao Xie, Yiqun Zhang, Yiu-ming Cheung

原文摘要

Time-series models are increasingly deployed in operational systems (e.g., inventory management and clinical care) where predictions trigger interventions that alter future observations, producing records we term AI-shaped trajectories. This sequence-prediction coupling deepens as such systems evolve into agents that autonomously predict, act, and remember across long horizons. Such AI-shaped trajectories support immediate performance monitoring, but turn ambiguous once reused as passive data. An algorithm may then misread a prediction-prevented stockout as naturally stable demand, or an averted medical crisis as a false alarm. This ambiguity then propagates into everything built on the record, from retraining and agent memory to downstream predictive tasks. As a result, systems may internalize these intervention effects as natural phenomena, drifting further from the truth at every closed-loop cycle. In this Blue Sky paper, we advocate an agenda for reflexive time-series analysis that shifts the analytical object from the intervention-agnostic sequence to the prediction-action-observation loop. The agenda requires closed-loop provenance to track the operational context (e.g., predictions, policies, and actions), sequence identification to estimate how those actions affect future values under explicit causal assumptions, and closed-loop evaluation to separate intrinsic process prediction from policy-driven effects. This foundation is essential for integrating autonomous agents into such loops at scale, enabling the joint learning of intervention effects and intrinsic dynamics for robust temporal representations.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02510

Neuro Inspired Robotics: What Robot Learning Can Borrow from the Sensorimotor Brain

Ruihan Zhang, Davy Deng

原文摘要

Robot policies still fail at everyday manipulation: an unfamiliar task, an object never held before, a scene that changes mid-motion, a skill that should improve with use. They fail despite pretraining on over a million trajectories, pooled from dozens of robots at great expense, while a child acquires all of these abilities within a few years of learning from a single body. This survey argues that the gap is one of design, and proposes designs for the next generation of robot models, drawn from how the nervous system solves the same problems. From the body we take compliance: the policy commands stiffness alongside position, so the controller yields where the task allows and presses where it must, which greatly lowers the demand for precise position output. From the visual system, where a fast pathway for action runs in parallel with the slow pathway for recognition, we take a dedicated fast vision system for motor behavior: it precomputes the quantities the policy needs and drives a reactive policy at camera rate. From the cerebellum we take a predictor beside the policy that forecasts the consequence of each command and recalibrates from its own error. From motor cortex we take a single model that composes action units from primitives, verifies each at a sensory boundary, practices the weakest unit with a hypothesis in mind, and reasons each attempt closer to the goal. Proven primitives are then consolidated from code into weights, so they run fluently and respond quickly the next time. Together these describe a robot that acts on its own initiative, the basis of deployment and recursive self-improvement, and we offer each proposal as a hypothesis to be tested.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02509

A balloon effect: ban one channel and a hidden trait finds another

Keuntae Kim, Yong Suk Choi

原文摘要

Language models trained on the outputs of other models can acquire traits that those outputs never mention, such as a preference for an animal carried by lists of numbers. Such subliminal learning can pass on unwanted traits. The intuitive defence is to find and forbid the tokens through which a trait shows, but how a trait's trace behaves under such bans, and what of it a student learns, has not been resolved. We closed a trait's outlets one by one in two stress tests, a preference chain and a name chain, across two models, six output formats and 16 traits. Bans did not remove the trait. Much as squeezing a balloon in one place makes it bulge in another, the trait moved to wherever the format still allowed, an effect we call the balloon effect. Decomposing this transfer, which bans on surface features cannot stop, down to single heads and neurons, we show that it can be cut at the circuit that writes the trait into the output. Patching that circuit while the teacher writes numbers stopped the chains, sharply reduced the overt name leak and halved the trait passed to a student, whereas the same number of random heads produced no detectable reduction. These results give a mechanistic account of how unwanted hidden traits are transferred and a route to preventing it.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02508

AttentionIndex: Accelerating Learned Sparse Attention with a Causal Inverted-File Index

Jeongmin Brian Park, Wen-mei Hwu

原文摘要

Learned sparse attention, used in production models such as DeepSeek-V4 and GLM-5, lets each query attend to only k keys chosen by a lightweight indexer, but the indexer still scores every key in the prefix. At one million tokens, this selection takes more than half of prefill time. Two-stage selection over contiguous blocks, as in HiSA, reduces this cost, but its recall declines as context grows at a fixed candidate budget. We present AttentionIndex, which routes each query over an inverted-file index that groups indexer keys by similarity and refines the candidates with the native indexer score. AttentionIndex builds the index during prefill, making new keys searchable immediately, reusing previous clustering to keep maintenance cheap, and exposing each query only to clusters built from its own prefix. On GLM-5.3 and DeepSeek-V4-Flash at one million tokens, AttentionIndex delivers 1.3-1.8 times the prefill throughput of exhaustive selection, and at throughput within 5% of HiSA, it recovers 17.0 and 10.0 percentage points more of the exhaustive top-k, respectively. AttentionIndex also improves accuracy on long-context benchmarks by up to 18.4 percentage points over HiSA at the same candidate budget.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.01055

MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Visual Reasoning

Jinwoo Kim, Rina Carines Cabral, Dhita Putri Pratama, Eileen Wang, Hiba Arnaout, Dhita Pratama, Shuo Yang, Dangyang Liu 等 14 位作者

原文摘要

Commonsense knowledge is widely used to support multimodal reasoning and generation, yet existing resources are predominantly text-only and lack grounding in visual context. This limitation often leads to the retrieval of semantically related but visually misaligned knowledge, and can degrade downstream performance. We introduce MMCOMET, a large-scale multimodal commonsense knowledge graph that integrates physical, social, and eventive knowledge with visual grounding. MMCOMET extends ATOMIC2020 by associating each commonsense triple with representative images through a hybrid alignment pipeline, resulting in over 900K multimodal tuples spanning 19 relation types. We further establish a unified evaluation framework across diverse vision-language tasks, including visual commonsense reasoning, visual question answering, visual storytelling, image editing, and image captioning. Our analysis shows that multimodal grounding provides more contextually aligned and reliable knowledge compared to both text-only knowledge graphs and LLM-based knowledge generation, particularly in reasoning-intensive scenarios. At the same time, we observe that the effectiveness of external knowledge is task-dependent, and naive knowledge integration can introduce noise in perception-dominated settings. To mitigate this, we propose an adaptive knowledge router that dynamically selects optimal paths or bypass knowledge in harmful settings. MMCOMET provides a scalable multimodal commonsense resource and a benchmark for studying the role of grounded knowledge in multimodal systems.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02503

Towards Multi-Value Alignment via Value Localization in LLMs

Xueqi Ma, Yanbei Jiang, Xingjun Ma, James Bailey, Sarah M. Erfani

原文摘要

Aligning large language models (LLMs) with multiple, potentially conflicting human values remains challenging, as existing multi-objective alignment methods often require costly fine-tuning and provide limited insight into the internal mechanisms underlying value-related behaviors. In this work, we investigate multi-value alignment from a mechanistic interpretability perspective by identifying value-sensitive attention heads (value heads) in LLMs. Using a probing-based value localization framework, we discover sparse sets of attention heads associated with diverse dimensions, spanning both human values (e.g., harmlessness, honesty) and stylistic preferences (e.g., coherence, complexity). Analyses across multiple LLM families reveal functional specialization and structured interactions among value heads, including conflicts between certain values. Targeted head ablations further induce substantial, value-specific behavioral changes, providing causal evidence of their functional importance. Building on these findings, we propose an inference-time activation steering strategy that enables controllable alignment with individual values or combinations of values without updating the underlying model parameters, supported by theoretical analysis. Experiments across multiple value alignment benchmarks demonstrate effective single- and multi-value control while largely preserving non-target model performance. Our findings connect mechanistic interpretability with flexible multi-value alignment, offering a foundation for more interpretable and pluralistic LLM behavior. The code is available at https://github.com/sihuo-design/ValueHeads.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02497

RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild

Tan Sang Nguyen, Yi Ru Wang, Shailesh Shailesh, Gang Yang, Jiamo Hu, Jianuo Jiang, Haoquan Fang, Zhongzheng Ren 等 27 位作者

原文摘要

General-purpose robot policies must work across robots, tasks, and environments, yet the variation that makes physical trials informative also makes them difficult to reproduce. We introduce RoboColosseum, a distributed evaluation framework that combines unified policy serving and standardized protocols across a network of locally operated robots in diverse environments. Our initial study evaluates five vision-language-action (VLA) policies and three frontier AI agents across four embodiments (SO-101, Franka, Bimanual-YAM, and G1 Humanoid). The Open Track compares models without task-specific adaptation in blinded, pairwise trials under matched local conditions. The Fine-tune Track measures how well VLA policies adapt to 20 tasks across all four embodiments when each policy receives the same 100 demonstrations per task. Across 5,699 pairwise Open Track comparisons at 124 sites, frontier agents rival specialized VLA policies, while all systems struggle to complete open-world tasks reliably. After fine-tuning, GR00T N1.7 leads on SO-101 and pi0.5 leads on Franka and Bimanual-YAM. Policy rankings show weak agreement across embodiment-specific task suites (Kendall W = 0.24). Open Track rankings poorly predict relative performance after fine-tuning, with substantial rank reversals on all three embodiments shared between tracks. Measuring partial progress reveals differences that task success alone misses. On the G1 Humanoid, no policy completes any of the five tasks, yet average progress ranges from 13.3% to 23.2% across policies. Open Track rankings stabilize as trials accumulate, and active matchmaking achieves comparable ranking agreement with substantially fewer physical trials than uniform sampling. These results show how distributed physical evaluation can reveal where robot policies generalize, how well they adapt to new tasks, and how far they progress on tasks they fail to complete.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.33702

Seeing the Options: What Should a Visual Candidate See?

Fengxin Li

原文摘要

Agents often choose among candidates that are images: elements of a screenshot, product photos, charts. A single-pass decision model either encodes the request and all candidates as one sequence, making its answer depend on candidate order, or encodes each candidate alone, which keeps order invariance and reusable encodings but hides the request from the candidate. We ask where the joint encoder's advantage comes from: from candidates seeing the request, or from candidates seeing each other while they are encoded. With one backbone and the same fine-tuning steps on screenshot crops of Multimodal-Mind2Web, the answer is mostly the request. Continuing each candidate from a forked cache of the encoded request recovers 11 to 13 of the 12 to 17 points that independent encoding loses to joint encoding, at the price of cross-request reuse, and we prove that order invariance stays exact whenever candidates never see each other. A joint encoder retrained with its candidates isolated from one another during encoding loses 1.1 and 0.4 ranking points in one paired run (0.7 and 0.3 against the mean of five joint runs), and permutation-equivariant interactions among candidates, over pooled vectors or inside the encoder, gain nothing beyond continued training. At a matched abstention operating point the state-conditioned model is 0.6 and 1.0 points below the joint encoder (mean of four runs) with a flip rate of zero, against 8-10% for the joint encoder; on AndroidControl crops (three and five runs) it is 2.5 to 4 ranking points below. Finally, the abstention threshold drifts: the choice term of the loss ignores the score level, and the coverage term pins it only weakly once positives saturate; a quantile threshold aligns operating points.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2509.22964

Functional Critics for Off-Policy Actor-Critic: From Stability to Exploration

Qinxun Bai, Yuxuan Han, Yuxiao Wen, Wei Xu, Zhengyuan Zhou

原文摘要

Actor-critic methods are central to modern reinforcement learning, yet off-policy actor-critic theory remains far removed from practical algorithms, due in part to the interaction between the deadly triad and the continually changing target policy. We revisit functional critics, i.e., value functions that explicitly condition on the policy, and show that this representation provides a shared foundation for off-policy training stability and policy-space exploration. We first develop a convergent off-policy actor-critic framework under linear function approximation that accommodates target-based TD, partial coverage, and evolving behavior policies. Our analysis combines a policy-evaluation guarantee under partial coverage with policy-gradient generalization of functional critics to yield a dual trust-coverage framework that controls policy-gradient error under evolving behavior policies while enabling greater reuse of off-policy data. We further develop a replay-buffer analysis under i.i.d. sampling, yielding a principled replay-sampling design for minimizing the replay-sample complexity required to reach a prescribed evaluation accuracy. We next show that functional critics provide a natural representation for model-free posterior-sampling-style exploration. Standard critic ensembles do not naturally represent joint uncertainty over return functions across policy space, whereas functional-critic ensembles represent policy-conditioned return functions directly. This motivates a particle-based, model-free analogue of posterior-sampling-style exploration without explicit model learning. Finally, we instantiate these ideas in a deep functional actor-critic algorithm that, despite omitting several standard off-policy AC heuristics, achieves strong performance across the full Dog and Humanoid task series of the DeepMind Control Suite.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02489

Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series

Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu

原文摘要

Industrial predictive maintenance and manufacturing tasks frequently contain abundant sensor measurements, but with limited labeled data. We investigate cross-domain self-supervised pretraining using joint-embedding predictive architecture for heterogeneous industrial time series (JEPA-HITS), which learns one encoder from various domains such as battery, semiconductor chemical mechanical planarization (CMP), computer numerical control (CNC) machining, and bearing while preserving dataset-specific temporal scales. We evaluate representation reuse on regression and classification problems under reduced-label downstream training, and leave-one-domain-out (LODO) pretraining. Compared with the same architecture initialized randomly, LODO pretraining reduces RMSE from 10.72 to 7.95 on battery remaining useful life (RUL), 4.34 to 3.89 on CMP, and 13.53 to 11.72 on tool wear regression, while improving bearing fault diagnosis macro-F1 from 0.547 to 0.737. Overall results suggest that unlabeled time series measurements from heterogeneous industrial processes can provide reusable representations for downstream learning with limited labeled data.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02487

RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms

Tingran Gan, Zhouziyue Lu, Dian Jin, Tao Li, Yang Gao, Ming Liu, Weiwen Liu, Jianghao Lin 等 10 位作者

原文摘要

Improving recommendation algorithms for the Web requires coordinating interacting design choices and learning from experiments. We present RecRSI, an LLM-based research framework that uses mechanism hypotheses to organize algorithm discovery. Each hypothesis links a proposed mechanism change to a reference design, a rationale, and an expected observation. MechSpace derives implementable primitives and composition rules from the task source; Research Line uses this space and prior evidence to develop and test hypotheses; Mechanism Feedback carries outcomes and their design context into subsequent research. This organization makes each experiment inform which mechanisms to develop, revise, or combine next. Across four initial recommenders and four datasets, RecRSI yields average relative improvements of 8.48% in NDCG@5 and 6.88% in HR@5 over the initial algorithms, and 2.60% and 2.20%, respectively, over the strongest competing result for each setting and metric. Component and process studies link these gains to coordinated mechanism choices and evidence-guided follow-up. Our code is publicly available at https://github.com/DynamisG210/RecRSI.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02484

Benchmark of THReD: Evaluating an LLM Agent and Its Preprocessing Tools for Turning Electronic Health Records into AI-Ready Datasets

Javad Mohammad Alizadeh, Huanmei Wu

原文摘要

LLM agents are increasingly built into data-analysis software, yet little evidence shows how reliably they preprocess clinical data or whether the tools they invoke give correct, reproducible output. We report a benchmark of THReD, a web-based system that turns electronic health record (EHR) extracts into AI-ready datasets through a chat agent whose proposed steps run only after user confirmation. The agent benchmark has 141 tasks (100 templates) in seven categories, including goal-level requests, failure recovery, requests calling for no action, schema variation and prompt injection through the data, on synthetic tables calibrated to a regional health information exchange; success is judged by checks on the produced data. Over 2,550 episodes with Claude Haiku 5.5 in four context configurations, the deployed agent completed 92.7% (95% CI 88.1-96.4) of tasks on its first answer, abstained on every advice request, recovered from every injected fault, and never proposed an action requested by planted text. Without the data profile, completion fell to 58.0%; goal-level requests were hardest (80.6%). Six experiments on real records of two chronic-disease cohorts and on synthetic data at scale validate the tools: 91-92% of inferred patient classes and 99.7-99.8% of inferred vital-sign labels were correct in masked reconstruction; a dictionary builder combining curated dictionaries with LLM suggestions mapped 99.0% of 2,208 raw variants correctly; all 2,176 replays of 128 saved pipelines gave byte-identical files under pinned dependencies; subgroup differences in inference accuracy vanished within facility and lookup key; and the same-day consolidation rule changed 90-day emergency revisit rates by up to 3.2 points without shifting cohort composition by more than one point. Processing time grew roughly linearly to 5.5 million records while the prompt stayed at about 13 thousand tokens.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09806

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

Songtao Wei, Yi Li, Zhikai Li, Xu Hu, Yuede Ji, Guanpeng Li, Feng Chen, Carl Yang 等 10 位作者

原文摘要

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require, wasting compute, latency, and context budgets. While introducing length-based efficiency rewards during reinforcement learning offers a natural remedy, existing methods struggle with two fundamental challenges: the optimal balance between correctness and efficiency is non-stationary throughout training, and intrinsic reasoning budgets vary drastically across problems. Relying on static reward weights and global length constraints inevitably forces a compromise between degraded accuracy and unrealized compression. To overcome these limitations, we propose LEAD (Length-Efficient Adaptive and Dynamic reasoning), a method that replaces static heuristics with online, self-adaptive mechanisms. LEAD dynamically calibrates the correctness--efficiency trade-off at each step using a Potential-Scaled Instability, directing optimization capacity to the most informative learning signal. Furthermore, it estimates an adaptive per-problem target length online based on the model's own correct rollouts, applying a symmetric efficiency reward that penalizes both overthinking and over-compression. Evaluated on five mathematical reasoning benchmarks, LEAD achieves the highest accuracy and Accuracy-Efficiency Score among RL-trained efficient-reasoning methods in our matched comparisons while producing substantially shorter outputs than the base model.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02480

Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory

Di Lu, Zechen Li, Hao Xue

原文摘要

Long-term conversational memory faces a timing mismatch: write-time summaries and graphs organize history before a future query is known, while independent retrieval can allocate a limited evidence budget to redundant or fragmented turns. We introduce Chain on Demand (CoD), a query-time evidence organization framework over an unchanged turn-level memory. Given a broad candidate pool, CoD constructs a temporary evidence chain by allocating a fixed anchor budget according to query relevance, lexical diversity relative to selected anchors, and newly covered query terms, followed by deterministic restoration of each selected anchor's same-session neighborhood. The resulting chain is used only for the current query, while the underlying conversational memory remains unchanged. In a paired comparison over all 1,986 LoCoMo questions, CoD achieves 82.2% accuracy on 1,540 non-adversarial questions and 76.3% on all 1,986 questions. On LongMemEval-S, one fixed configuration that indexes both user and assistant turns obtains 86.6% across all 500 questions. These results show that long-term memory can preserve the original conversation while deferring evidence organization until the information need is known.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.34428

AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Question Answering over Scientific Citation Graphs

Chanhee Park, Jeongho Yoon, Sungbin Han, Hyeonseok Moon, Heuiseok Lim

原文摘要

Agentic tasks require a large language model to interact with the world, navigating information and gathering evidence across multiple steps with restricted resources. Due to this complexity, agentic task failures arise from various sources, and pinpointing these failure causes is essential to diagnose and improve agentic systems. Existing benchmarks, however, tend to focus on a single leaderboard score, leaving the underlying failure modes opaque. To fill this gap, we introduce AgentHop, a diagnostic benchmark of 1,011 multiple-choice questions paired with a controlled seven-tool sandbox under fixed token, turn, and tool-call constraints. AgentHop reveals model vulnerabilities by dissecting a single accuracy score along four axes of agent operation: retrieval, synthesis, tool-call, and resource management. Across 19 models, we find that behavior clusters by model family, with tool-call signatures revealing distinct family fingerprints: GPT models commit early, Anthropic and GLM checkpoints verify before committing, DeepSeek and Kimi over-search, and Gemini-3 Pro stays balanced. Decomposed axes further expose within-family structure: Claude Opus 4.6 and Sonnet 4.6 land within one accuracy point yet diverge on retrieval-versus-synthesis emphasis, with Opus retrieving more and Sonnet synthesizing better. We release the full benchmark set and the harness to support diagnostic agent benchmarking.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.08239

When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding

Yiheng Wang, Yueqian Lin, Lichen Zhu, Yudong Liu, Hai "Helen" Li, Yiran Chen

原文摘要

Multimodal large language models (MLLMs) have made substantial advancements in video understanding, yet the reliability of their responses remains underexplored. This work presents a diagnostic study of absent answer detection for MLLMs in video understanding, where the correct answer is deliberately excluded from the candidate set and a reliable model is expected to recognize that no valid option exists. We evaluate the absent answer detection behavior under three settings: multiple-choice questions augmented with a ``None of the Above'' option, open-ended generation with a detection instruction, and standard evaluation without any guidance. Across a diverse set of models and benchmarks, we find that MLLMs overwhelmingly select plausible distractors rather than detecting the absent answer. This failure is more pronounced in temporal reasoning tasks and worsens with denser frame sampling. We further explore chain-of-thought prompting as a mitigation strategy and find that while it substantially improves detection rates, performance remains unsatisfactory, suggesting that prompting-based strategies alone are insufficient to fully address this limitation. These findings expose a systematic failure in absent answer detection and highlight the need for explicit detection mechanisms in multimodal systems.

cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02472

MAGAR: Multimodal Agents for GUI-Based 3D Mechanical Assembly and Minimal Rework

Jingxuan Wei, Jiahao Fu, Fuqiang Wang, Xiaoming Wu, Yuwen Liu, Kaiwen Wei, Ming Yang, Junnan Zhu

原文摘要

A GUI command can be correct at the interface level yet still produce an incorrect assembly. An agent must identify the relevant components, respect their structural relationships, and determine which parts should move during recovery. We introduce MAGAR-Bench, a benchmark of 4,000 multimodal samples from 26 assembly families that separates Assembly Decision, Atomic Action, and Minimal Rework. For rework, the objective counts distinct moved parts within the validated recovery candidate set for each state, rather than the number of actions. We also introduce MAGAR, a selective correction framework built on a frozen policy obtained by supervised fine-tuning. Its key design matches correction granularity to output dependencies. Structured candidates revise assembly fields and rework scope, while complete action candidates keep native GUI primitives coupled with their parameters. A learned selector retains the original prediction unless a candidate passes a task-specific intervention threshold. On recorded states from held-out assembly families, MAGAR improves Overall, the task-balanced aggregate, from 37.50 to 41.39, with gains on all three tasks. Across 209 interventions, 70 correct an error and 22 introduce one. These results support task-specific correction while highlighting the remaining tradeoff between fixing errors and preserving reliable predictions.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23344

Language Models Learn to Improve Language Models

Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He, Zhan Shi, Benoit Dumoulin, Xiang Zhang 等 10 位作者

原文摘要

Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning experimental feedback into a learned ability to propose effective improvements across models faces two challenges. First, training such an ability with real feedback is expensive: reinforcement learning (RL) requires evaluating tens of thousands of proposals, each potentially requiring a full model-training run. Even at ten GPU-hours per run, reward collection alone would consume hundreds of thousands of GPU-hours, motivating a cheaper surrogate. Second, surrogate feedback can become unreliable as policy optimization favors overestimated proposals when the proposal distribution shifts. To address these challenges, we propose LM2LM, which trains LLMs with RL to generate effective LM improvement proposals. To provide scalable feedback, we use a research world model (RWM), a frozen LLM that predicts proposal gains from real experimental records provided in context, as the reward model for RL. To maintain feedback reliability, we periodically execute current-policy proposals ranked highly by the RWM and add their measured outcomes to its context. Across eight autoregressive and diffusion LM development environments, real-execution evaluations on held-out tasks show that LM2LM enables Qwen3.8-27B to outperform GPT-6-sol, even when GPT-6-sol is given 300 real experimental records in context, while requiring 33% lower data-generation cost. LM2LM also generalizes to a model family unseen during training.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02463

Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation

Yuxuan Hu, Yingyi Zhang, Wenlin Zhang, Chao Zhang, Haotian Nan, Ziwei Liu, Jiancheng Dong, Tongzhou Wu 等 14 位作者

原文摘要

Semantic-ID-based (SID) generative recommendation (GR) represents each item as a sequence of discrete tokens and predicts the next item through autoregressive SID generation. However, existing methods face two challenges. First, insufficient shared context modeling for user sequences: full-history and recent behaviors provide overlapping yet complementary evidence, but modeling them within a single sequence may dilute current cues, whereas processing them through separate streams may fail to coordinate them. Second, insufficient personalized adaptation in progressive SID decisions: although decoder states evolve with generated prefixes, existing models typically use a shared output-side transformation across recommendation instances, without explicitly selecting a transformation suited to the current user need. To address these challenges, we propose Multi-View Thinking with Adaptive Generation (MV-Thinker), a framework that Thinks Globally and Generates Personally. First, Multi-View Temporal Thinking uses view-specific thinking queries and readers over overlapping full-history and recent-history views, coordinating both sources into complementary user-conditioned contexts before SID generation. Second, Hierarchical Residual Adaptation organizes lightweight adapters into nested residual paths before a shared vocabulary projection, adaptively transforming context-bearing decoder states for SID decisions. Extensive experiments on four public datasets demonstrate that MV-Thinker consistently outperforms strong discriminative and generative recommendation baselines across multiple ranking metrics. The implementation code and datasets are available on: https://anonymous.4open.science/r/MV-Thinker

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02457

Multi-Teacher Reasoning Distillation for LLM Recommendation with Self-Exploration

Liangbo Ning, Siyuan Liang, Yi Zhou, Yifeng Zhang, Qing Li, Wenqi Fan, Dacheng Tao

原文摘要

Reasoning-augmented recommender systems (RecSys) enhance user preference modeling by generating reasoning trajectories over historical interactions before making recommendations. Knowledge distillation provides a practical paradigm for transferring such reasoning capabilities from powerful large language models to lightweight RecSys. However, existing methods typically rely on a single fixed teacher, remain constrained by the teacher knowledge ceiling, and indiscriminately distill teacher-generated trajectories without assessing their actual utility for downstream recommendation. To address these limitations, we propose MUSE (Multi-Teacher Utility-guided Selection with Self-Exploration), an adaptive reasoning distillation framework that jointly improves reasoning generation and reasoning utilization. MUSE first constructs a diverse reasoning pool using multiple teacher LLMs and progressively augments it via student self-exploration, enabling the student to leverage the strengths of different teachers and gradually explore reasoning strategies beyond teacher imitation. We then develop Rank-Gain Utility Assessment (RGUA), which evaluates each candidate according to the normalized full-catalog rank improvement of the ground-truth item and identifies the most and least recommendation-beneficial trajectories. Based on these utility-aware trajectory pairs, we introduce dual-level contrastive learning objectives that guide the student generator to prefer beneficial reasoning while training the recommendation encoder to more effectively exploit recommendation-relevant preference evidence. Extensive experiments on three real-world datasets demonstrate the effectiveness and robustness of the proposed framework.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗