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

+1196新增论文
+992其中 AI 相关
+66已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 11:15 · 全站最近入库：2026-11-10 11:14各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 12:11 — 2026-11-10 12:11（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：2026-11-10 11:15最近发现新增版本：2026-11-10 11:14库内论文最新更新时间：2026-11-08 04:43

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。

19,084 已收录论文16,280 AI 相关4,962 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 16,280 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 11:14（北京时间）
版本更新 · v2arXiv:2610.31090

Poolwise: Evaluating Reward Models for Selection across Prompts

Mateusz Modrzejewski, Tomasz Radzikowski

原文摘要

Reward models are used to select training data, but common benchmarks compare responses only within the same prompt. Selecting data across prompts also depends on how scores compare between prompts. We introduce Poolwise, a protocol that selects a fixed fraction of a response pool by score, measures the selected set's quality using external labels, and reports within-prompt ranking separately. In matched experiments on two rating sets and two model sizes, training each prompt's mean score to match its average response rating improves selection over permuted or omitted mean targets in every seed at 30 percent retention. In grouped HelpSteer experiments, the model with the highest within-prompt accuracy selects a lower-rated set than the correct-mean model. Subtracting prompt means estimated from separate reference responses preserves local rankings but lowers selected helpfulness for six open reward models and two closed judges on HelpSteer. Poolwise provides a direct way to compare reward models and score transformations for data selection.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02028

LARK: Lean-Assisted Reasoning for LLM-Generated GPU Kernels

Zixi Zhang, Jiayi Nie, Haoran Wu, Yujie Yan, Yann Herklotz, Rika Antonova, Robert Mullins, Yiren Zhao 等 10 位作者

原文摘要

Efficient GPU kernels are typically low-level and hardware-specific, and LLM agents can now generate them faster than experts can verify. Existing approaches rely on testing, which provides evidence but not a guarantee of correctness. We introduce LARK, an agentic framework that automatically and formally verifies GPU kernels against their PyTorch reference implementations. LARK proves equivalence in functional and memory behavior under exact arithmetic and establishes a new trust boundary: human effort is only needed to verify operator-level Lean semantics ahead of kernel generation time, instead of checking every single line of generated code. LARK formalizes the GPU machine model and the semantics of each operation in Lean 4 once per target language, and the Lean 4 semantics of any incoming kernel is derived from these pre-built definitions. LLM agents then automate the proof in two steps. First, an agent decomposes the whole kernel semantics into smaller segments and Lean 4 verifies this segmentation, which addresses the intractability of proving equivalence for large kernels directly. Second, agents write Lean proofs that each kernel segment matches its high-level PyTorch counterpart. Together, the two steps give whole-program equivalence. We demonstrate that LARK can be used 1) to ensure correctness in existing code-generation agents and 2) to automatically verify human-written kernel libraries. On the KernelCraft GPU tasks, combined with a simple ReAct agent, LARK enables GLM 5.3 to fully verify 10 of 12 Level-1 kernels and Opus 5.5 all 5 Level-2 kernels. Moreover, over 10 production kernels randomly sampled from popular open-source LLM serving frameworks, LARK verifies 9 and identifies a new data race bug in the tenth. We believe LARK represents a significant step toward verifiable code generation in the agentic era.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.02686

Fooling Reward Models with Gibberish: Adversarial Examples Beyond the Semantic Regime

Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang

原文摘要

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF). We show that leading RMs can assign higher scores to gibberish than to meaningful reference answers. To systematically discover such inputs, we introduce Token Mapping Perturbation Attack (TOMPA), a framework that uses a perturbed token mapping to extend an attack LLM's search beyond natural language. The mapping changes the linguistic meaning of the attack LLM's natural language responses, producing non-linguistic text for the target RM to score. We then use these scalar scores as rewards to train the attack LLM through reinforcement learning to discover non-linguistic adversarial inputs. Experiments against Llama and Qwen RMs demonstrate such attacks using two instantiations: identity token mapping across different tokenizers and random permutation with a shared tokenizer. Against Skywork-Reward-V2-Llama-3.1-8B, ranked first on RewardBench 2, the two mappings achieve mean rewards of +33.64 and +43.78, respectively, compared with +17.48 for GPT-5 reference answers. Their attack success rates are 97.6% and 100%, measured as the percentages of individual responses scoring above their corresponding GPT-5 references. These results show that strong benchmark performance does not ensure robustness to non-linguistic adversarial inputs, exposing a fundamental vulnerability in using RMs as optimization targets.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02027

Uncertainty-Aware 3D Position Reconstruction in CZT Drift-Strip Detectors

Alejandro Valverde Mahou, Michał Kossakowski, Selina R. H. Owe, Rikke S. Klausen, Irfan Kuvvetli, Christian A. Naesseth, Søren Hauberg

原文摘要

Accurate three-dimensional interaction-position reconstruction is important for CZT drift-strip detectors, but conventional methods can suffer from degraded performance in challenging detector regions, while learned models provide limited information about prediction reliability. We investigate two uncertainty-aware approaches: deep ensembles of point-estimation networks and simulation-based inference (SBI), which estimates a posterior distribution over interaction position. Both approaches are trained on physics-based simulations and evaluated on both synthetic and experimental data. On synthetic data, uncertainty from both methods correlates with positioning error, with SBI showing a substantially stronger relationship. On experimental measurements, the deep ensemble achieves improved $z$-position resolution, while SBI provides more informative uncertainty estimates that highlight regions of reduced positional information and discrepancies between simulation and the physical detector. These results demonstrate the complementary strengths of ensemble-based reconstruction and posterior inference for uncertainty-aware detector position reconstruction.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02026

Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in Large Vision-Language Models

Junfei Wu, Qiuyue Wang, Xuhong Huang, Qihang Peng, Mingsheng Li, Jian Guan, Qiang Liu, Shu Wu 等 11 位作者

原文摘要

The spatial intelligence of large vision-language models (LVLMs) requires the ability to combine local visual observations into a geometrically consistent representation of the physical world. Many static benchmarks assess isolated spatial judgments, such as relative direction or distance, while interactive embodied evaluations combine perception with exploration, planning, control, and simulator-specific execution. To bridge this gap, we introduce RECONSPATIAL, a benchmark centered on multi-view 3D scene reconstruction across indoor, tabletop, and outdoor environments. Given real multi-view images and target-object queries, LVLMs are required to jointly predict oriented 3D bounding boxes in a shared, camera-anchored metric coordinate frame. Reconstructions are evaluated along two complementary axes: Structure for relative layout and Metric for physical scale and camera-anchored placement. Nine atomic spatial QA tasks, grouped into Geometric Perception and Spatial Relations, probe spatial capabilities involved in joint reconstruction. Offline navigation extends evaluation to path planning. Evaluation of 18 frontier LVLMs reveals a consistent gap between relative scene structure and metric reconstruction; even GPT-6-Astra scores 81.4% on Structure but only 58.7% on Metric. Tracing this gap, diagnostic analyses link atomic spatial capabilities to reconstruction quality and show that relational consistency alone does not ensure metric accuracy. Experiments with 3D map injection further separate scene construction from path planning, revealing how these geometric errors limit navigation success. Finally, spatial fine-tuning yields broad transfer across both spatial and general vision-language benchmarks.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02021

ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies

Bahar Radmehr, Lan Tran, Ekaterina Shved, Fatma Bet{ü}l G{ü}reş, Adish Singla, Tanja K{ä}ser

原文摘要

Digital learning environments produce rich clickstream data that can reveal how students approach learning tasks, yet interpreting these fine-grained traces often requires substantial expert effort. We introduce ClickSight, a framework for interpreting student clickstreams through learning strategies defined in the literature. Given a student clickstream and a predefined set of learning strategies, ClickSight uses a staged LLM-based pipeline to identify strategy-relevant evidence, assess adherence to each strategy, and generate an evidence-grounded interpretation of the student's behavior. We evaluate ClickSight across two learning environments, 365 students, and 12 model backbones using an expert-grounded quality rubric and an LLM judge calibrated with human-expert ratings. Our results show that ClickSight can generate high-quality strategy-based interpretations across different models and environments, with reasoning models performing more consistently than instruction-tuned counterparts. We further find that providing external clickstream-extracted guidance can improve interpretation quality for strategies that require precise quantitative information from the trace. By connecting fine-grained clickstreams with theoretically defined learning strategies and preserving the evidence underlying each judgment, ClickSight provides a flexible approach for studying student behavior in digital learning environments.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02019

Multi-criteria Rating and Review based Recommendation Model

Emrul Hasan, Chen Ding, Alfredo Cuzzocrea

原文摘要

These days, due to the advancement of information technology, recommendation system has become one of the key tools for e-commerce business. E-commerce platforms allow users to provide feedback in both written comments and numerical ratings. Recommendation systems are utilized to recommend users to new or unseen items based on these previously collected comments or ratings. In recent years, multi-aspect or multi-criteria based recommendation systems have been studied a lot by the recommendation research community. However, these research works are conducted either with reviews or ratings, not with both. In this project, we argue that integrating both textual reviews (with multiple aspects) and numerical multi-criteria ratings can further enhance the overall rating prediction accuracy. We propose a Multi-criteria Rating and Review based Recommendation model (MRRRec). We show that incorporating multi-criteria ratings into multi-aspect ratings from reviews has a great impact on performance. Our proposed model outperforms several state-of-the-art models such as ANR, DeepCoNN, and Deep Multi-criteria Recommendation System in terms of MSE, MAE, precision, recall, and F1. We show that our proposed model achieves an average of 19% and 23.0% lower MSE and MAE respectively and 7.0%, 1.0% and 3.8% higher precision, recall, and F1 score respectively. We further show that our model performs significantly better with Word2Vec word embedding than the GloVe word embedding method.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02018

CULTURE-CMT: Benchmarking Contextualized Social Media Translation

Linjuan Wu, Dingming Li, Yiwen Qiu, Xinze Lyu, Ye Guo, Daoxin Zhang, Zhe Xu, Weiming Lu

原文摘要

Social-media comments are interactions, yet they are often translated and evaluated as isolated text. This mismatch is especially problematic when meaning depends on surrounding discussion, community-specific slang, or culturally situated expressions. We introduce CULTURE-CMT, a Chinese-English benchmark for contextualized social-media comment translation that restores the post and conversational context naturally available to users. Its 572 manually verified examples are organized into Slang, Context, and Both, enabling diagnostic analysis of distinct and interacting sources of translation difficulty. To support scalable evaluation, we further develop a retrieval-augmented cultural-effectiveness Judger that combines a calibrated scoring model with dynamically retrieved cultural knowledge. CULTURE-CMT reveals several non-trivial patterns. Providing interaction context improves most model configurations, but does not eliminate culturally ineffective translations. Examples requiring both contextual grounding and culturally situated language remain substantially more difficult than either source of difficulty alone. Moreover, larger models are not consistently better, and thinking produces highly model-dependent gains, including occasional degradation. In contrast, a 27B model adapted on benchmark-disjoint social-media data achieves the lowest observed invalidity rate among the evaluated configurations under thinking inference with context. Together, these results suggest that realistic social-media translation is not simply a matter of scaling models or reasoning longer, but of learning to translate meaning as it is constructed within evolving online interactions.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02017

Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?

Shuochen Chang, Qianli Ma, Yibo Miao, Qingyang Liu, Bingjie Gao, Haonan Zhao, Siyu Sun, Yulin Sun 等 10 位作者

原文摘要

Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, they need to recover an earlier task's requirements and partial progress after intervening work. Existing repository-level benchmarks typically score one issue-to-patch episode and do not directly measure whether an agent can resume a task after advancing other unfinished work in the same repository. We introduce \textbf{\ourmethod}, a benchmark for focus-task resumption in sessions that interleave unfinished tasks drawn from the same source repository, with a persistent checkout for each task. Each focus task is evaluated in matched uninterrupted and switched sessions with identical focus requirements and executable verifiers. The switched session interleaves ordered stages from other unfinished tasks in the same repository, while only the final focus patch is scored. \ourmethod~contains 200 focus tasks from 19 Python repositories, reconstructed from issue, pull-request, and review histories and rendered as 400 matched session specifications. Across 7 coding agents, interleaved unfinished work produces an average focus-task resolution gap of 11.5 percentage points, ranging from 6.0 to 15.0 percentage points. Trajectory analysis identifies cross-task requirement confusion and loss of task state as recurrent resumption behaviors. We introduce a plug-in context-management module that selects task-relevant history and maintains concise task-state summaries. On OpenCode, the module improves focus-task completion under same-repository task switching by 5.5 to 15.5 percentage points across the evaluated models. Code is available at github.com/Miraclecsc/Switch-SWE.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02015

Scaling Makes It Possible: How Large Models Master Impossible Languages

Yaning Jia, Chunhui Zhang, Chiyu Ma, Zhongyu Ouyang, Ivory Yang, Soroush Vosoughi

原文摘要

While language models (LMs) excel in natural language tasks, their ability to learn impossible languages--those that violate the structural, cognitive, or logical constraints that make human languages learnable and functional--remains debatable. This controversy is further fueled by a divide between linguistic theorists and empirical researchers working with small-scale LMs. To address this controversy, we introduce semantic coherence. This concept measures how effectively semantic information is expressed in language structures and examines the learning capabilities of LMs across multiple scales. By fine-tuning billion-parameter LMs on impossible language samples, we demonstrate that larger LMs achieve similar performance on impossible and possible languages, whereas million-parameter LMs exhibit significant degradation when trained on impossible languages. This performance gap widens as semantic complexity increases. We further show that scaling up the LM size fundamentally shifts the learning focus from grammatical rules to semantic understanding, with billion-scale LMs exhibiting a threefold reduction in sensitivity to low-level linguistic perturbations while maintaining stable performance under high-level semantic perturbations.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.27606

Ask to Learn: Query-Based Collaborative Reinforcement Learning

Kaicheng Zhang, Hongqian Niu, Laixi Shi, Didong Li, Guannan Qu, Zhun Deng

原文摘要

Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, unsafe, or infeasible. We study whether this limitation can be overcome without directly interacting with the underlying environment. Motivated by practical settings such as collaborator-mediated simulation, where a collaborator can provide information complementary to the offline data, we introduce query-based collaborative reinforcement learning to study how to acquire this information efficiently. The learner starts with a fixed offline dataset and adaptively queries state-time pairs; the collaborator samples an action according to a fixed, possibly suboptimal policy, and the simulator returns the corresponding reward and next state. For finite-horizon tabular problems, we derive an instance-dependent information-theoretic lower bound on the additional queries required to identify an $ε$-optimal policy and develop a local quadratic approximation. Guided by this characterization, we develop an adaptive query-allocation algorithm whose query complexity nearly matches the local benchmark under suitable conditions. Experiments on multiple synthetic and semi-synthetic environments demonstrate the empirical efficiency of the proposed method.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.23335

The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models

Moshiur Farazi, Sameera Ramasinghe, Bekir Sait Ciftler, Mahbub Ahmed Turza, Shafin Rahman

原文摘要

Auxiliary signal pathways in VLMs are routinely fitted with learnable gates so the optimiser can decide how much of the signal to admit. We study what the optimiser decides, and whether the model then uses the signal, with hyperbolic visual relational graphs as the experimental vehicle. We find that under cross-entropy fine-tuning the optimiser decides on zero: the gate closes in every design we trained, across five injection designs on LLaVA-1.5-7B, 15 of 15 runs on Qwen2-VL-7B spanning four task families, 3 of 3 seeds on InternVL3-8B, and with LoRA on all linear layers. We attribute this suppression phenomenon to two regimes, a dead-gradient regime formalised through the caption-invariance of image-derived signals and measured directly, and a negative-utility regime in which the auxiliary signal actively hurts the loss. A closed gate does not by itself mean an inert pathway, so we ablate each pathway at inference under one protocol with real region proposals: the norm-aligned designs are behaviourally closed (at most 1.5pp change at the learned gate), whereas the un-normalised gated prefix is open and harmful, costing 6.7pp on relational GQA at its learned gate of +0.005 while helping SugarCrepe. Evaluating every configuration under one inference mode shows that an active injected pathway costs up to 15pp on relational GQA and 7-12pp on out-of-distribution VSR, that the geometric training losses give no measurable in-distribution gain once the pathway is dropped, and that a Euclidean containment control ties the hyperbolic one. Embedding-norm alignment remains necessary for prefix injection that preserves generation. We recommend testing signal use by ablation rather than by reading gate values or attention mass. We open-source the implementation, the checkpoints and the result files behind every table at https://github.com/mrfarazi/the-gate-always-closes.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02011

MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment

Davide Vitabile, Alexandro Buffa, Akshay Nambiar, Amril Nazir

原文摘要

Medical language models promise expert clinical support, but the strongest open-source LLMs remain too large for private edge-device deployment, while compact medical models still trail substantially on knowledge-intensive and real-world healthcare tasks. Reasoning models that fit edge memory budgets can produce long reasoning traces, increasing sequential decoding, end-to-end latency, energy consumption, and KV-cache memory pressure. We present MedPsy, a family of text-only 1.7B and 4B medical language models designed for edge deployment, targeting this accuracy-generation-efficiency trade-off. Our recipe combines a synthetic medical data pipeline over biology, medicine, and health seeds with chain-of-thought targets from a 235B medical-focused LLM teacher; a four-stage post-training curriculum comprising two SFT stages followed by two RL stages with hard-sample mining; and an edge deployment evaluation spanning multiple GGUF quantization variants and real-device inference on laptop and smartphone hardware. On seven closed-ended medical benchmarks, MedPsy-4B surpasses MedGemma-1.5-4B by 19.34 points and matches MedGemma-27B while being 6.75x smaller; MedPsy-1.7B outperforms MedGemma-1.5-4B by 11.42 points despite being less than half its size. On HealthBench-Hard, MedPsy-4B surpasses MedGemma-27B by 15.33 points, while MedPsy-1.7B surpasses it by 11.66 points despite being ~16x smaller. Beyond accuracy, MedPsy reduces average response length by 1.7x (1.7B) and 3.2x (4B) versus its Qwen3 backbones, while Q4_K_M quantization preserves the aggregate score within 1 point of BF16 with ~69% lower disk footprint. In real-device inference, MedPsy-4B's shorter generations translate into 75% lower median end-to-end latency and estimated energy per answer than its Qwen3 backbone at matched quantization, while peak RAM remains below 5 GB across our tested laptop and smartphone configurations.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02009

Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training

Linjuan Wu, Yiwen Qiu, Xinze Lyu, Dingming Li, Hui Yao, Zhongyi Sang, Ye Guo, Daoxin Zhang 等 14 位作者

原文摘要

Social media translation requires preserving meaning while capturing the cultural nuances of user-generated content (UGC). However, gaps in the cultural knowledge of LLM-based evaluators can lead to inaccurate assessments and unreliable training rewards. To improve these signals, we use retrieval-enhanced cultural evaluation to train CUE-MT, a family of social media translation models. A calibrated, domain-specific Judger guides supervised data refinement and is augmented by an Agent for hard-example mining and reinforcement learning. The Agent retrieves relevant external evidence as needed and distills it into concise hints that the Judger uses to score translations and assign rewards. Across 9B, 27B, and 35B-A3B backbones, CUE-MT outperforms the evaluated open-source baselines of comparable size on CUE-MT-Bench and three public benchmarks. Human evaluation on CUE-MT-Bench shows cultural effectiveness gains of 7.44-15.12 percentage points over the strongest external baseline in each size group. Retrieval improves the Judger's four-way classification accuracy by 8.07 percentage points over a matched no-retrieval baseline that uses LLM-generated hints alone. Training ablations further support the combination of hard-example mining and Agent-enhanced rewards.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02008

NAS-PO: Native Attention-Strategy Policy Optimization for Vision-Language Models

Ke An, Shizhe Xiang, Yue Liu, Liang Chen, Pei Fu, Shaojie Zhang, Xiaoxing Hu, Yupei Wang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has become an effective post-training paradigm for vision-language models (VLMs). Standard RLVR, however, assigns identical outcome-derived credit to all generated tokens regardless of their perceptual relevance. Recent perception-aware methods estimate visual reliance through image perturbation or masking. These indirect proxies require perturbation branches, while corruption sensitivity does not necessarily identify the visual evidence used for reasoning. We instead shape model perception through native attention, an intrinsic model signal. Rather than treating attention as a post-hoc explanation, we formulate it as a reward-anchored, token-aligned routing signal that encourages attention patterns supporting visually grounded reasoning. To this end, we propose NAS-PO, a Native Attention-Strategy Policy Optimization framework. NAS-PO analyzes native attention with a visual mass policy that quantifies visual allocation and a conditional visual policy that captures spatial routing over visual tokens, making the optimization well-posed. Based on this, Native Attention-Strategy Advantage Shaping (NAS-AS) draws on the visual-mass policy to redistribute signed policy-gradient credit for visually engaged rollouts. The Adaptive Attention-Coupled (AAC) loss then aligns the visual-mass policy on all response tokens and the conditional visual policy on visually active ones, consolidating the visual-routing patterns that drive successful trajectories. Experiments demonstrate that NAS-PO substantially surpasses leading RL-tuned VLMs across 7 out-of-domain reasoning and perception benchmarks, with its effectiveness consistently validated across 8B and 32B. Visual-Routing Sensitivity (VRS) analysis further indicates that the optimized attention prioritizes visually load-bearing regions.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02003

MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation

Hyeongyu Kim, Mingyeong Jang, Youngjun Song, GeonHui Han, Dosik Hwang

原文摘要

Test-time adaptation (TTA) updates a deployed model using only unlabeled target data, but standard entropy-based methods often rely on deterministic confidence and can reinforce overconfident errors under distribution shift. We propose MIRA, Mutual Information guided calibration for Reliable Test-Time Adaptation, a source-free online adaptation method that uses lightweight last-layer Gaussian perturbations to probe prediction reliability. For each target batch, MIRA reuses a single feature extraction pass and samples perturbed classifiers around the source classifier, forming an efficient local predictive distribution. Rather than fitting a Bayesian posterior, MIRA treats the perturbation scale as a local probing radius and selects a batch-specific scale using mutual information (MI) and prediction agreement. The resulting perturbation-sensitivity signal identifies predictions that are confident and locally stable under classifier perturbations, while suppressing brittle predictions with high stochastic disagreement. MIRA then performs adaptation with an MI-confidence weighted entropy loss, which down-weights perturbation-sensitive or low-confidence samples before they drive entropy minimization. This weighted loss reduces the influence of brittle predictions that can otherwise cause harmful adaptation under distribution shift. The method requires no source data, retraining, model ensembles, or offline posterior fitting, and can be applied as a plug-and-play modification to entropy-minimization TTA. Experiments on distribution-shift benchmarks show improvements in accuracy, calibration, and negative log-likelihood, suggesting that mutual-information-guided perturbation probing and weighted adaptation yield more robust online TTA than deterministic confidence.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02002

To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments

Bahar Radmehr, Jiaxu Zhao, Fatma Betül Güreş, Adish Singla, Tanja Käser

原文摘要

Simulated students offer a scalable way to test learning platforms and AI tutors before deployment with real students and to augment scarce data for studying learning at scale. Existing LLM-based simulators primarily target short, language-centered interactions. In open-ended learning environments, however, student behavior emerges from patterns across long-horizon interaction trajectories, where turn-level prompting can drift from an assigned behavior profile. We introduce ALPS (Align Long-term by Planning Short-term), a hierarchical simulated student conditioned on observable, environment-specific behavior profiles. Rather than selecting every action independently, ALPS alternates between planning profile-aligned task segments and generating the corresponding actions. We evaluate ALPS in both data-sufficient and data-scarce settings, where supervision comes either from real student trajectories or from a teacher LLM. Across both settings, we compare in-context learning (ICL), supervised fine-tuning (SFT), reward-ranked fine-tuning (RAFT), and their sequential combination (SFT followed by RAFT). Experiments in an inquiry-based physics game and a pharmacy simulation evaluate behavioral density and coverage against held-out real data, and profile consistency using a human-aligned LLM judge. Across both settings, ALPS consistently outperforms turn-level generation, achieving comparable density and judge pass rates under scarce supervision, although coverage remains lower. These results show that hierarchical planning enables faithful, profile-aligned simulation over long interaction horizons, even with limited real student data.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02001

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui, Lok Kan Chan, Ginny Y. Wong, Simon See

原文摘要

Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical lenses. Memory systems that retrieve the passages most similar to a question, or the most recent ones, therefore return superseded values, miss rules that share no wording with the question, and cannot recover a stance spread across sessions. We present TrackMem, a per-speaker graph memory that tracks the history of figures, separates perspectives by entity and lens, and preserves each speaker's actions in chronological order. To evaluate it, we introduce FinLoCoMo, a benchmark of 15 long-horizon investment conversations with 765 questions in two splits: one following the LoCoMo categories and one targeting four failure modes. With two readers, TrackMem outperforms existing memory systems on both splits. On the failure-mode split it reaches 73.9% macro accuracy against 69.4% for the strongest baseline, with the largest gains on questions about revised figures (86.5% against 73.4%).

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.26065

Kernel Ridge Regression over Hölder Classes: Function and Derivative Losses

Yuxuan Hou, Yicheng Li

原文摘要

We study ordinary kernel ridge regression over full Hölder-Zygmund balls, measuring errors in Sobolev norms and in pointwise and uniform losses for mixed derivatives. For targets of smoothness $s$, every RKHS norm equivalent to $H^{s+d/2}$ gives the optimal $H^r$ risk for $0\le r<s$; integer choices of $r$ include integrated squared derivative losses. Pointwise and uniform guarantees require additional kernel structure. A localized wavelet kernel attains the sharp derivative rates with the same regularization orders as for function estimation, whereas equivalent changes of the RKHS norm can destroy the population bias rates. For the ordinary Gaussian kernel with a shrinking bandwidth, we prove a uniform derivative risk bound with the optimal polynomial rate and an explicit, unoptimized logarithmic factor. The results allow bounded measurable design densities bounded away from zero and conditionally sub-Gaussian noise.

stat.ML · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22061

FAOPs: Normal Forms and an Algebra for AI Agent Workflows

Ali Mohammadi Shanghooshabad

原文摘要

Organizations increasingly encode operational procedures as multi-step agent skills, here called Agent Operating Procedures (AOPs), that must be traceable, auditable, reproducible, access-controlled, and bounded in time and cost, as regulated sectors require. Yet AOPs are typically kept as coarse-grained files, in which steps bundle actions, copied procedures drift apart, any step may reach any tool, and refactoring goes unchecked. We present Functional Agent Operating Procedures (FAOP), a formal theory that brings database-grade discipline to AI agent workflows. FAOP recasts each workflow as a typed function over scoped state and subjects an entire library to four progressive normal forms: Decomposed (FNF-1) splits a workflow into atomic steps, Typed (FNF-2) makes its data flow explicit and type-checked, Factored (FNF-3) gives each shared sub-workflow a single canonical definition so a change propagates instead of drifting, and Scoped (FNF-4) checks that each FAOP lists resources used by its own actions and the FAOPs it calls, while guardrails declared by it and by FAOPs that call it remain attached to their sources. A FAOP algebra of provably sound equalities turns refactoring and parallelization into compiler rewrites; orthogonal extensions add optimization (+O), bounded completion with time and cost limits (+B), and reachability checks (+R); and an architectural-level classifier (0-3) determines whether a workflow needs AI at all. Together, these make integrity, isolation, typing, stopping limits, cost, and optimization compile-time concerns across the whole library, not runtime hopes. We implement the theory in SkillBase, an AOP management system (what PostgreSQL is to data, SkillBase is to AOPs), and a separate executor that loads FAOPs from SkillBase and enforces these guarantees at run time. A worked financial workflow illustrates the approach end to end.

cs.AI · cs.DB · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01996

Safety4DM: A Vision-Language Framework for Risk-Aware Dynamic Maps in Vehicle-Road-Cloud Collaborative Driving

Zhengshu Zhou, Shaoyu Wang, Lu Tao, Xinhui Hu, Jiaqi Gu, Tingting Zhao

原文摘要

Dynamic map (DM) is a core information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving. It fuses perception data from multiple sources to overcome the inherent line-of-sight and field-of-view limits of single-vehicle perception. However, DM still falls short on driving safety in two ways. First, DM data specifications already define road conditions semantically, but no pipeline yet turns real-world road observations into fine-grained risk entities in the DM. Second, existing DM systems lack a natural language interface for driving risks. To close these gaps, we propose Safety4DM, a safety-oriented language system for VRC dynamic maps. We first build RoadRisk, a real-world road image dataset that covers four types of road conditions and four risk levels. On this dataset, we fine-tune a vision-language model (VLM) for road safety risk perception. The model outputs structured risk representations that the DM can ingest directly. We then introduce a Safety-aware Step-wise Prompting (SafeStep) mechanism as the natural language query interface of the DM. SafeStep answers queries accurately and also generates actionable driving advice. To build and evaluate this interface, we develop SafeVRC-Sim, a VRC cooperative simulation framework, and SafeDM-QA, a safety question-answering benchmark. Experiments show that even the compact Qwen3-VL-4B reaches 89.83% accuracy on risk perception after fine-tuning. SafeStep also plugs easily into multiple LLM families. With medium and large models (20B and above) from five families, it achieves over 93% natural language query accuracy in every case, which shows strong generalization.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.23983

Community HydroAgent: Formalizing Forecaster Expertise into Skill-Orchestrated Flood Forecasting Workflows

Qingyi Yang, Siqian Qiu, Bing Li, Xu Shan, Jia Feng, Shunan Zhou, Xudong Zhou, Tiantian Xing 等 23 位作者

原文摘要

Operational flood forecasting depends on tacit forecaster expertise that is difficult to formalize, audit, and transfer. Although artificial intelligence methods have advanced flood prediction and model-error correction, few studies explicitly represent the tacit expert rules, review checkpoints, and workflow constraints that connect model outputs to operational warning decisions. Here, we propose Community HydroAgent for Flood Forecasting (CHA-Flood), a skill-orchestrated agent framework that embeds Large Language Models (LLMs) into a model-driven flood forecasting workflow, where each skill encodes explicit rules to bound LLM reasoning. We validated its effectiveness using five state-of-the-art LLMs in the South Yamhill River basin (USA). Prior judgment captures observed peak flow and flood volume within 5% tolerance in 10 and 11 out of 14 events, and 5-fold cross-validation over 129 events yields Pearson correlations of 0.62 and 0.84. Building on a high-baseline scheme library (average KGE 0.890), the guided scheme selection further improves KGE by 0.023-0.154. All five tested LLMs successfully execute the CHA-Flood workflow with comparable judgment accuracy (each spanning 40%-80% across cross-validation folds) but with substantial cost differences. Removing only the language-model narrowing lowers median KGE from 0.723-0.753 to 0.662 for all five LLMs, indicating that the gain comes from LLM reasoning rather than from the choice of LLM. CHA-Flood does not aim to replace human forecasters; instead, it translates their tacit expertise into an auditable and reproducible workflow. This skill-orchestrated paradigm demonstrates how explicit rule boundaries can guide LLM reasoning to complement physically based simulation in next-generation flood forecasting.

physics.geo-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01992

Cross-Dataset Generalization of Glaucoma Detection CNNs: Effects of Operating Threshold, Multi-Source Training, and Color Normalization

Al-Amin Rahman, Saifuddin Ahmed, Resalat Ahmed

原文摘要

Deep learning models for glaucoma detection are usually tested on images from the same dataset used for training. That says little about how they will work at a new hospital or with a new camera. We fine-tuned five ImageNet-pretrained CNNs (ResNet50, DenseNet121, MobileNetV2, EfficientNet-B0, InceptionV3) with identical settings on one of three public fundus datasets (ACRIMA, ORIGA, RIM-ONE DL). Each was tested on a held-out part of its own dataset and on the other two datasets in full. We used three random seeds and report mean and SD over seeds. Mean in-domain AUC was 0.913 and cross-source AUC was 0.702, a drop of 0.211 (SD 0.030; 95% CI 0.135 to 0.286). After correction for multiple comparisons we found no evidence that any architecture did better, though three seeds give low power. At thresholds set on the source validation data, specificity fell from 0.870 to 0.506 and sensitivity from 0.831 to 0.726. Resetting the threshold on 10% of the target images raised specificity to 0.670 but lowered sensitivity to 0.609, and balanced accuracy rose only from 0.616 to 0.639. Training on two sources together did not help (held-out AUC 0.695 versus 0.702). LAB reference normalization (cross-source AUC 0.755) and strong color augmentation (0.754) gave similar gains, cutting the drop to about 0.16. Ben Graham normalization (0.733) and CLAHE (0.712) helped less, and gray-world (0.696) did not help. The two best methods raised specificity but lowered sensitivity. On G1020, used only for testing, AUC stayed near 0.5 in every condition, and networks trained within G1020 were also close to chance. Strong in-domain results do not show that a glaucoma model will work on new data. Normalization and color augmentation reduce the drop but do not remove it. Studies should report external validation and check the operating threshold, not only AUC.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19690

PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations

Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui

原文摘要

We prove that computing a complete contiguous $\varepsilon$-envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness holds even when $\varepsilon$ is given in unary, and even when every density takes only the values $λ$ and $2λ$ for some $λ>0$ common to all agents and has at most six breakpoints. As a consequence, computing an exact contiguous envy-free allocation is also PPAD-complete, even under the same density restrictions. Our key ingredient is to assign prices to the pieces so that, in every approximately envy-free allocation, all prices are nearly equal, regardless of how the pieces are assigned to the agents. We further show that, for every fixed integer $c\ge1$, computing a contiguous allocation of indivisible goods on a path that is envy-free up to $c$ goods (EF$c$) is PPAD-complete for additive valuations, and this remains true even for $c=\lfloor m^α\rfloor$ with any fixed rational $0<α<1$, where $m$ is the number of goods. This hardness holds even for binary valuations in which each good is valued by exactly one agent and all agents value the same number of goods. All these results extend to chores. Our results answer three open questions at once: whether contiguous envy-free cake cutting is PPAD-hard for additive valuations, the complexity of computing contiguous EF1 and EF2 allocations of goods on a path, and the corresponding question for EF1 allocations of chores.

cs.GT · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01990

Synthetic Realities: Evaluating Human Ability to Distinguish AIGenerated Videos from Real Footage

Danyal Sarfraz, Raja Mubashar Karim, KwanMyung Kim

原文摘要

Recent advances in generative AI have enabled multiple pathways for high-fidelity video synthesis: text-to-video, image-to-video animation, and video outpainting. Empirical side-by-side evaluations of how untrained viewers perceive and distinguish these outputs from real footage remain scarce. In this study, we systematically compare human detection accuracy across these three AI generation techniques within three thematic contexts: historical footage, film and media content, and natural environments. We constructed a balanced stimulus set comprising equal amounts of real and AI-generated videos (18 each). The AI clips were evenly distributed across the three generation methods using Google's Veo 3, Lightricks LTX Video, and Wan VACE. All videos were produced and standardized within the ComfyUI framework to ensure consistent quality and duration. 87 participants judged every clip in a binary forced-choice task ("real" vs. "AI-generated"). Participants correctly identified videos 60% of the time on average. Image-to-video clips were recognized most accurately (79%), followed by real footage (64%), outpainting (49%), and text-to-video (43%). Accuracy also varied by theme: film and historical scenes yielded higher detection rates than environmental clips, which were frequently mistaken for AI. Logistic regression confirmed significant effects of both technique and theme as well as their interaction (p < 0.001), indicating that detection success depends jointly on how the content was generated and what it depicts. Findings reveal a consistent bias toward assuming synthetic origins and highlight that perceptual realism in AI video is shaped more by context than by model type, underscoring the importance of media-literacy approaches and context-aware evaluation tools for navigating increasingly synthetic visual media.

cs.CV · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01987

Same Trajectory, Different Knowledge: Information-State-Aware On-Policy Distillation for Search Agents

Minhao Sun, Xian-Ling Mao, Eric Tao, Zi-Ao Ma, Zhijing Wu

原文摘要

On-policy distillation trains search agents with teacher feedback on student-generated trajectories. Recent methods augment the teacher's context with supporting evidence, reference answers, or hindsight information. However, this privileged information may allow the teacher to rely on facts that the student cannot reliably recover from its current state. The resulting information-state mismatch can lead the teacher to undervalue retrieval that helps the student establish those facts. To address this mismatch, we introduce Information-State-Aware Distillation (ISA-Distill), which adapts teacher feedback to the student's factual recoverability. ISA-Distill estimates how reliably the student can recover action-relevant knowledge and derives teacher feedback for the same sampled action from two complementary views. The fact-use view supplies the teacher with the relevant fact, producing feedback that guides the student in using knowledge. The evidence-seeking view instead presents the information need, producing feedback that guides the student in acquiring supporting evidence. The two signals are weighted toward fact use when recoverability is high and toward evidence seeking when it is low, and the resulting feedback guides policy optimization. Experiments across diverse QA benchmarks and model scales demonstrate improved answer accuracy and retrieval efficiency. Our code and model checkpoints will be open-sourced.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30168

Finitely Verifiable Segmentation: Decidability for Every Tokenizer with a Finite-State Verifier

Nicklas Nidhögg

原文摘要

A segmentation policy assigns to each byte string at most one segmentation into tokens. Call it finitely verifiable when a finite automaton over marked strings, bytes paired with boundary bits, accepts exactly the policy's own segmentations. The automaton judges a proposed segmentation and need not compute one. From a supplied verifier the paper gives constructive decisions for four questions, whether a window certifies a token boundary, whether the boundary gap is bounded, whether a mask can keep generation from dead-ending, and whether two policies are equivalent. The last three specialize limitedness, co-accessibility and the equivalence of single-valued transducers. The first refines the synchronizing cut of code theory, and two more ask whether a certified cut, or the cuts of an inventory, let each piece scan alone. The class sits strictly between the online-scannable policies and those with regular domains, and online scannability is decidable in polynomial time through Choffrut's theorem. Markings are length-preserving, so the class is exactly the rational segmentation policies, a normal form rather than a restriction. The class is closed under four pipeline operations, composition over a labeled stage, restriction to a regular schema, splitting at character-class changes, and byte-fallback union of literal policies. Each composite inherits the six decisions, and certificates transfer between stages under four laws. Under rational, unifilar, almost surely stopping finite-state sources, each mass of the weighted section is an exact rational, and so is each rate where expected length is positive. Maximal-munch lexing, canonical byte-pair encoding and two-mode WordPiece instantiate the interface, and the munch library implements all six decisions. Every theorem carries an executable check, and every reported statistic is a program's own output.

cs.FL · cs.CL · cs.PL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.23299

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

Yidong Luo, Chenguang Wang, Fangzhou Zhu, Tao Zhong, Tianshu Yu

原文摘要

Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptimal settings can degrade solving time by orders of magnitude. Default configurations are often suboptimal, while traditional tuning methods either suffer from the ``cold-start'' problem and inefficient search or heavily rely on expert experience. This paper introduces \textbf{GRIMIP} (\textbf{\underline{G}}eneral \textbf{\underline{R}}easoning for \textbf{\underline{I}}nstance-specific \textbf{\underline{MIP}} configuration), a novel hybrid intelligence framework that synergistically integrates the semantic reasoning capabilities of Large Language Models (LLMs) with the sample-efficient search of Bayesian Optimization (BO). GRIMIP enables the LLM to function as a complete probabilistic surrogate within the BO loop, significantly improving performance and reducing sampling and evaluation costs. On seven benchmarks including MIPLIB, GRIMIP achieves over 40\% reduction in Primal-Dual Integral on hard instances, outperforming SMAC and other LLM-assisted BO methods. By granting LLMs sufficient autonomy, GRIMIP combines the expert-level reasoning of LLMs with the efficient search of BO, achieving state-of-the-art performance.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01986

RubricWorld: World Model-Guided Rubric Optimization for LLM Graders

Hongji Pu, Hang Li, Yucheng Chu, Jiliang Tang

原文摘要

Rubric optimization improves LLM grading by revising scoring instructions while keeping the grader's parameters fixed. Existing optimizers often judge edits by aggregate validation performance, limiting the supervision they retain about which errors an edit corrects or introduces. Testing each candidate also requires rescoring validation answers, which limits how many edits can be explored within a fixed budget. We propose RubricWorld, a framework that learns from previous edit evaluations to guide further search. Its world model predicts an edit's correction and degradation rates at score boundaries, conditioned on the current rubric state. The training signal comes from paired grading results: scores for the same answers before and after an edit. Predictions select one candidate for direct evaluation, and held-out confidence bounds determine whether it corrects enough target errors while keeping new errors within prespecified limits. Measured effects update the model even when the edit is rejected. Across EIR (National), ASAP2.0, and ASAP-SAS with three frozen LLM graders, RubricWorld achieves the highest score in 20 of 27 metric comparisons. On ASAP2.0, it raises gpt-5-mini accuracy from 18.20% with the original rubric to 46.70%, exceeding the strongest baseline, APO, by 22.60 percentage points. code will be released upon acceptance.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01984

Large-Scale Bayesian Optimisation Using Uncertainty-Calibrated Product-of-Experts Gaussian Process Models with Trust Regions

Yean Hoon Ong

原文摘要

The use of collections of independent local Gaussian processes (GP-ind) combined with trust regions is a widely adopted approach for large-scale and high-dimensional Bayesian optimisation (BO). However, this approach suffers from several limitations, including discontinuities at the boundaries of disjoint regions, an inability to capture long-range spatial correlations, potential information loss, and abrupt increases in computational overhead. To address these limitations, this paper introduces a novel BO algorithm, termed BO-pro-c-tr. The proposed method employs a product-of-experts Gaussian process model with uncertainty calibration (GP-pro-c) as its surrogate model and incorporates a one-to-many association strategy for integrating GP-pro-c with trust regions. Empirical results suggest that, when combined with the GP-LCB acquisition function, BO-pro-c-tr achieves an average reduction of 2.6% in simple regret and 34.9% in computational overhead relative to BO algorithms based on independent local GP models coupled with trust regions.

cs.LG

查看论文
arXiv ↗PDF ↗