Artificial Intelligence Paper Rankings

Artificial Intelligence Paper Rankings

AI-estimated scientific impact ranking of the latest arXiv Artificial Intelligence preprints. Methodology New: General Relativity

Sign up for free to unlock all papers & more

Sign up

Artificial IntelligenceMachine LearningMachine Learning (Statistics)RoboticsQuantum Physics

More

Suggest

Filter by tags

200papers (279 total)

51350matches

Newly Added Last 7 Days Last 30 Days All Time

Archive

#PaperScore95% CIMatchWin %RatingGapPublished

1Towards a General Intelligence and Interface for Wearable Health DataGirish Narayanswamy, Maxwell A. Xu +61643±314379.1%8.20May 21, 20262Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable AlignmentZhiqin Yang, Yonggang Zhang +41589±383461.8%6.5+27.4May 20, 20263KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth ScienceZiwei Li, Liujun Zhu +61582±452290.9%7.8+0.2May 18, 20264The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less SecureQiqi Liu, Thorsten Holz +21563±452185.7%7.8\-0.8May 17, 20265Advancing Mathematics Research with AI-Driven Formal Proof SearchGeorge Tsoukalas, Anton Kovsharov +61563±502190.5%9\-2.4May 21, 20266Hallucination as Exploit: Evidence-Carrying Multimodal AgentsGuijia Zhang, Hao Zheng +11558±462065%7.2+5.1May 18, 20267Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific DiscoveryXinzhe Yuan, Zhuo Chen +51553±452085%7.2+4.8May 18, 20268TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination ReductionTej Sanibh Ranade1546±453770.3%5.5+54.4May 18, 20269Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM AgentsAhmad Al-Tawaha, Shangding Gu +31541±432580%7.3+0.9May 18, 202610What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure CodeYuze Zhao, Junpeng Fang +61539±452290.9%7.3+0.5May 19, 202611SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition ModulesYuxuan Chen, Changwei Lv +61535±472281.8%5.8+42.1May 21, 202612Efficient Agentic Reasoning Through Self-Regulated Simulative PlanningMingkai Deng, Jinyu Hou +51534±502295.5%7.2+2.2May 21, 202613Learning to Hand Off: Provably Convergent Workflow Learning under Interface ConstraintsJiayu Li, Enpei Zhang +31528±472286.4%7.8\-5.4May 18, 202614Generative Recursive ReasoningJunyeob Baek, Mingyu Jo +4v21523±431968.4%6.5+20.4May 19, 202615ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention SimulationZhikang Chen, Yue Wang +51519±462080%6.8+9.7May 17, 202616Gated DeltaNet-2: Decoupling Erase and Write in Linear AttentionAli Hatamizadeh, Yejin Choi +11518±501888.9%6.8+9.6May 21, 202617Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift CorrectionJiahe Guo, Xiangran Guo +61518±472584%7.2\-0.8May 18, 202618Echo: Learning from Experience Data via User-Driven RefinementHande Dong, Xiaoyun Liang +61513±481675%5.5+48.6May 21, 202619Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning ModelsJunyao Yang, Chen Qian +51511±471877.8%4.5+69.1May 18, 202620How Far Are We From True Auto-Research?Zhengxin Zhang, Ning Wang +21511±472755.6%7+1.9May 18, 202621Beyond Mode Collapse: Distribution Matching for Diverse ReasoningXiaozhe Li, Yang Li +61510±471485.7%5.8+37May 19, 202622Forecasting Scientific Progress with Artificial IntelligenceSean Wu, Pan Lu +61510±473036.7%7.4\-5.9May 21, 202623DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon DerivationSixiong Xie, Zhuofan Shi +61507±463336.4%6.8+7.2May 20, 202624Not all uncertainty is alike: volatility, stochasticity, and explorationPayam Piray1503±472181%7.5\-8.9May 19, 202625SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented ReasoningYufei Ma, Zihan Liang +61502±412475%7\-0.7May 18, 202626PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent OptimizationWonjoong Kim, Yeonjun In +31500±462080%6.8+5May 18, 202627What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language ModelsPayal Chandak, Victoria Alkin +61499±462483.3%7.5\-10.1May 18, 202628Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters MostNick Merrill, Jaeho Lee +11498±492382.6%7.8\-12.2May 21, 202629PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language ModelsZiliang Zhao, Zenan Xu +61498±471471.4%6.2+24May 20, 202630AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent WorkflowsShuaike Shen, Wenduo Cheng +31492±433070%6.2+22.2May 19, 202631Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive DomainsRebecca Ramnauth, Drazen Brscic +11492±461872.2%6.5+12.8May 19, 202632Latent-space Attacks for Refusal Evasion in Language ModelsGiorgio Piras, Raffaele Mura +51492±481782.4%7.8\-14May 20, 202633SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?Kevin Han, Renfei Zhang +41490±502483.3%7.5\-12.9May 20, 202634MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent SystemsQianshu Cai, Yonggang Zhang +51487±411866.7%4.8+55.3May 21, 202635OpenComputer: Verifiable Software Worlds for Computer-Use AgentsJinbiao Wei, Qianran Ma +51482±452176.2%7\-6.5May 19, 202636PEEK: Context Map as an Orientation Cache for Long-Context LLM AgentsZhuohan Gu, Qizheng Zhang +21482±451872.2%7.2\-10.6May 19, 202637Reliability and Effectiveness of Autonomous AI Agents in Supply Chain ManagementCarol Xuan Long, David Simchi-Levi +41481±462373.9%7.5\-15.5May 16, 202638ADR: An Agentic Detection System for Enterprise Agentic AI SecurityChenning Li, Pan Hu +61479±452369.6%7\-7.4May 17, 202639AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit AssignmentZhenlin Wei, Pu Jian +61477±452268.2%5.5+38.5May 18, 202640GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable RewardsKyeongjin Ahn, Seungeon Lee +21476±422369.6%7\-8.2May 19, 202641AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI CollaborationJiaqi Liu, Shi Qiu +61475±422774.1%6.5+7.6May 19, 202642Open-World Evaluations for Measuring Frontier AI CapabilitiesSayash Kapoor, Peter Kirgis +61475±422065%6.5+7.6May 19, 202643Causal Evidence for Attention Head Imbalance in Modality Conflict HallucinationJinrui Jiang, Zhangtai Wu +21475±442466.7%6.5+7.6May 19, 202644Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM AgentsTianshi Xu, Huifeng Wen +11475±471668.8%6.8\-2.4May 21, 202645GIM: Evaluating models via tasks that integrate multiple cognitive domainsRohit Patel, Alexandre Rezende +11474±432462.5%6.8\-2.9May 18, 202646Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem SolvingOussama Zenkri, Oliver Brock1471±442272.7%5.2+42.5May 19, 202647Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver SynthesisFatemeh Haji, Javier Delarosa Quiros +11468±431968.4%6.8\-5.4May 17, 202648Conflict-Aware Additive Guidance for Flow Models under Compositional RewardsXuehui Yu, Fucheng Cai +31468±442774.1%7.3\-18.3May 20, 202649Latent Action Reparameterization for Efficient Agent InferenceWenhao Huang, Qingwen Zeng +6v21466±461861.1%6.2+13.8May 18, 202650Measuring Cross-Modal Synergy: A Benchmark for VLM ExplainabilityJoël Roman Ky, Salah Ghamizi +11466±491675%7.2\-16.1May 21, 202651Harnessing LLM Agents with Skill ProgramsHongjun Liu, Yifei Ming +21463±461758.8%6.5+3.1May 18, 202652Generative AI and the Productivity Divide: Human-AI Complementarities in EducationLihi Idan, Bharat Anand1463±451968.4%4.5+54May 18, 202653Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill LibrariesXing Zhang, Yanwei Cui +51462±461450%5.8+21.6May 19, 202654Interactive Evaluation Requires a Design ScienceKeyang Xuan, Peiyang Song +61460±421662.5%6.5+1.7May 18, 202655Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM AgentsXing Zhang, Yanwei Cui +51456±491478.6%6.5\-0.2May 21, 202656ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time ScalingWoomin Song, Beomjun Kim +51455±432065%7\-17.1May 21, 202657Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less CostSimon Dennis, Rivaan Patil +21453±472070%6.5\-1.7May 21, 202658Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVRUtkarsh Tyagi, Xingang Guo +61452±461758.8%6.5\-2.4May 19, 202659Episodic-Semantic Memory Architecture for Long-Horizon Scientific AgentsNikola Milosevic1452±411650%4.5+48.5May 17, 202660MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data SynthesisHaiyang Shen, Taian Guo +61450±481275%6.5\-3.6May 20, 202661Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM AgentsAkshay Manglik, Apaar Shanker +6v21450±472166.7%6.5\-3.6May 20, 202662Mind the Sim-to-Real Gap & Think Like a ScientistHarsh Parikh, Gabriel Levin-Konigsberg +21450±422462.5%6.8\-13.6May 20, 202663Learning Quantifiable Visual Explanations Without Ground-TruthAmritpal Singh, Andrey Barsky +31449±451450%4.5+46.8May 18, 202664CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language ModelsYuning Wu, Yingmin Liu +11449±452075%5.8+15.1May 17, 202665Democratizing Large-Scale Re-Optimization with LLM-Guided Model PatchesTinghan Ye, Arnaud Deza +31448±451855.6%7\-21May 18, 202666Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented ReasoningZihan Liang, Yufei Ma +51447±481675%5.5+24.8May 21, 202667Position: The Turing-Completeness of Real-World Autoregressive Transformers Relies Heavily on Context ManagementGuanyu Cui, Zhewei Wei +11447±452254.5%6.8\-15.3May 19, 202668EXG: Self-Evolving Agents with Experience GraphsYuxin Jin, Siyuan Zhang +41445±421758.8%6.3+0.2May 18, 202669ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams UnderstandingMingyang Rao, Kehua Feng +51445±402653.8%6.8\-16.1May 17, 202670POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM AgentsQiaoyuan Zheng, Yiqu Yang +21444±392560%6.8\-16.6May 18, 202671Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision SupportChen Zhan, Xihe Qiu +61443±442070%6+5.8May 21, 202672Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict ContextsAndrii Kryshtal1442±491877.8%5.8+11.9May 21, 202673AMEL: Accumulated Message Effects on LLM JudgmentsSid-ali Temkit1441±481973.7%6.5\-8.1May 21, 202674CLORE: Content-Level Optimization for Reasoning EfficiencyYuyang Wu, Qiyao Xue +51441±481560%6.5\-8.1May 21, 202675Is VLA Reasoning Faithful? Probing Safety of Chain-of-CausationNicanor Mayumu, Xiaoheng Deng +11440±402055%5.5+21.2May 17, 202676What and When to Distill: Selective Hindsight Distillation for Multi-Turn AgentsXiaozhe Li, Tianyi Lyu +61439±451764.7%6.5\-9.2May 19, 202677A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark GenerationQingchuan Ma, Yuexiao Ma +41439±422060%5.8+9.9May 17, 202678CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic MaterialsYanjie Li1438±412055%4.5+41.2May 17, 202679Beyond Rational Illusion: Behaviorally Realistic Strategic ClassificationXinpeng Lv, Yunxin Mao +61438±402250%5.5+20.3May 19, 202680AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image AlignmentKuei-Chun Kao, Daixuan Huo +21437±442060%6.8\-20.2May 17, 202681Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG ClassificationYang Wu, Xiaoyan Yuan +21436±441861.1%6.8\-20.9May 17, 202682Actionable World RepresentationKunqi Xu, Jitao Li +51436±441758.8%5.5+19.1May 18, 202683Probabilistic Tiny Recursive ModelAmin Sghaier, Ali Parviz +11432±452161.9%5.8+6.1May 19, 202684Explainable Wastewater Digital Twins: Adaptive Context-Conditioned Structured Simulators with Self-Falsifying Decision SupportGary Simethy, Daniel Ortiz Arroyo +11432±452157.1%7.8\-39.8May 19, 202685SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated ObjectsPuyi Wang, Yuhao Wang +51432±442458.3%6.2\-3.6May 19, 202686Responsible Agentic AI Requires Explicit ProvenanceJinwei Hu, Xinmiao Huang +41431±442259.1%5.5+16.5May 16, 202687Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMsJunyu Pan, Yansen Wang +41431±441861.1%5.8+5.7May 18, 202688Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System PromptsZhiyuan Jerry Lin, Benjamin Letham +31430±382250%6.5\-13.9May 18, 202689Implicit Safety Alignment from Crowd PreferencesQian Lin, Daniel S. Brown1430±501457.1%6.5\-13.9May 20, 202690PALS: Power-Aware LLM Serving for Mixture-of-Experts ModelsCan Hankendi, Rana Shahout +21428±452152.4%6.5\-14.8May 20, 202691Latent Heuristic Search: Continuous Optimization for Automated Algorithm DesignCheikh Ahmed, Mahdi Mostajabdaveh +11428±441957.9%5.8+4.4May 16, 202692Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?Caixin Kang, Tianyu Yan +61427±501560%7.5\-40.4May 21, 202693Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction PerspectiveJunpeng Zhang, Lei Cheng +41426±442360.9%5.8+3.2May 18, 202694What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented ConstructMeryl Ye, Lujain Ibrahim +61425±491850%7\-32.4May 20, 202695DocOS: Towards Proactive Document-Guided Actions in GUI AgentsJingjing Liu, Ziye Huang +61424±432250%5.5+13.8May 18, 202696Skill Weaving: Efficient LLM Improvement via Modular SkillpacksZhuo Li, Guodong Du +61423±472055%6.2\-7.1May 21, 202697Conflict-Resilient Multi-Agent Reasoning via Signed Graph ModelingLonggang He, Longzhu He +21422±442552%5.5+13May 19, 202698LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent SystemsSadia Asif, Mohammad Mohammadi Amiri +31422±481457.1%6.8\-27.1May 21, 202699ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM ReasoningYeqiu Chen, Ziyan Liu +41421±461866.7%6.5\-17.5May 21, 2026100Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPsPierre Boudart, Pierre Gaillard +11419±421758.8%7.8\-45.4May 19, 2026101FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming RecommendationXinhang Yuan, Zexi Huang +61419±501747.1%7.2\-39May 20, 2026102Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent FrameworkMengyu Sun, Ziyuan Yang +41418±451747.1%5.8\-0.1May 18, 2026103IdleSpec: Exploiting Idle Time via Speculative Planning for LLM AgentsDaewon Choi, Kyunghyun Park +51418±481662.5%7\-35.5May 21, 2026104Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language ModelsWeicong Ni, Tianbao Jiang +11418±441861.1%5.2+17.3May 19, 2026105DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic WorkflowsYuxuan Gao, Megan Wang +31417±412045%6.5\-19.5May 18, 2026106Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in NanomedicineChristiaan G. A. Viviers, Koen de Bruin +61416±412864.3%4.8+23.9May 18, 2026107\\ECUAS{n}: A family of metrics for principled evaluation of uncertainty-augmented systemsLautaro Estienne, Erik Ernst +31415±442360.9%7\-36.4May 19, 2026108Dynamics of collective creativity in AI art competitionsMason Youngblood, Jeff Nusz +11415±451855.6%6.5\-20.1May 16, 2026109Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable SensorsYadhu Kartha, Conor Anderson +61414±422060%4.8+23.1May 17, 2026110Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidenceFiona Y. Wong, Markus J. Buehler1414±401844.4%5+18.9May 21, 2026111AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report GenerationShiying Yu, Jielei Wang +11413±431844.4%6.2\-12May 16, 2026112Neurosymbolic Learning for Inference-Time ArgumentationGabriel Freedman, Adam Dejl +51413±402759.3%5.5+8.6May 19, 2026113GraphMind: From Operational Traces to Self-Evolving Workflow AutomationYiwen Zhu, Joyce Cahoon +61410±421957.9%6.5\-22.7May 17, 2026114AI for Auto-Research: Roadmap & User GuideLingdong Kong, Xian Sun +61409±441747.1%6.5\-23May 18, 2026115Scalable Environments Drive Generalizable AgentsJiayi Zhang, Fanqi Kong +61408±441952.6%5.5+6.8May 18, 2026116SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational ScienceNithin Somasekharan, Youssef Hassan +61407±432152.4%7.2\-43.9May 18, 2026117QQJ: Quantifying Qualitative Judgment for Scalable and Human-Aligned Evaluation of Generative AIMarjan Veysi, Pirooz Shamsinejadbabaki +21407±432356.5%3.5+41.9May 17, 2026118Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache CompressionWei Luo, Yi Huang +41405±481758.8%5.8\-5.3May 21, 2026119DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEGYang Shao, Peiliang Gong +21405±432263.6%6.5\-24.5May 18, 2026120OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision ModelsChiara Maria Russo, Simone Carnemolla +41405±432055%5.5+5.5May 18, 2026121Causal Intervention-Based Memory Selection for Long-Horizon LLM AgentsSaksham Sahai Srivastava1405±431855.6%4.5+26.4May 17, 2026122SkillGenBench: Benchmarking Skill Generation Pipelines for LLM AgentsYifan Zhou, Zhentao Zhang +61405±441855.6%5.8\-5.3May 18, 2026123Self-supervised Hierarchical Visual Reasoning with World ModelYuanfei Xu, Lin Liu +31404±402343.5%5.8\-5.9May 17, 2026124Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA AgentsZijian Du, Nathaniel Pinckney1404±481650%5.5+5May 20, 2026125Unlocking Proactivity in Task-Oriented DialogueHongbin Zhang, Ning Gao +61404±481855.6%7.2\-45.4May 21, 2026126Memory-Augmented Reinforcement Learning Agent for CAD GenerationYin Xiaolong, Liu Yu +51403±442339.1%5.5+4.5May 19, 2026127ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMsBingjun Luo, Tony Wang +21403±461450%6.8\-35.5May 21, 2026128The Impact of AI Usage and Informativeness on Skill Development in Logical ReasoningShang Wu, Hongyu Yao +41403±471973.7%5+14May 20, 2026129MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill OptimizationMd Mehrab Tanjim, Jayakumar Subramanian +61403±422147.6%5.8\-6.4May 19, 2026130Divergence-Suppressing Couplings for Rectified FlowYimeng Min, Carla P. Gomes1402±431752.9%5.5+4.2May 18, 2026131Interaction Locality in Hierarchical Recursive ReasoningYosuke Miyanishi, Tetsuro Morimura1401±432360.9%4.8+17.6May 20, 2026132Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement LearningBanghao Chi, Yining Xie +61401±472055%6\-13.5May 21, 2026133TaskGround: Structured Executable Task Inference for Full-Scene Household ReasoningZhiYuan Feng, Yu Deng +61400±411838.9%6.8\-36.6May 18, 2026134Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning ModelsZheng Lin, Zhenxing Niu +31399±441952.6%6.8\-37May 19, 2026135Interference-Aware Multi-Task UnlearningYing-Hua Huang, Rui Fang +21398±412650%6.5\-27.7May 18, 2026136AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image PromptersHanjun Luo, Zhimu Huang +61397±412445.8%7.2\-48.7May 21, 2026137Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool UseChangkun Ou1396±412050%5.2+8.1May 18, 2026138PRISM: A Benchmark for Programmatic Spatial-Temporal ReasoningQiran Zhang, Yuheng Wang +61393±421942.1%6.5\-29.7May 19, 2026139AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from InteractionsMinghao Chen, Xinyi Hu +21393±412653.8%6.8\-39.7May 20, 2026140Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code OptimizationDmitry Redko, Albert Fazlyev +41393±421855.6%6.8\-39.7May 19, 2026141TerminalWorld: Benchmarking Agents on Real-World Terminal TasksZhaoyang Chu, Jiarui Hu +61392±471560%6.8\-40May 21, 2026142Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical PlanningMichael Aichmüller, Simon Ståhlberg +21392±432653.8%7.8\-56.7May 18, 2026143CAM-Bench: A Benchmark for Computational and Applied Mathematics in LeanWentao Long, Yunfei Zhang +41391±402356.5%6.5\-30.2May 17, 2026144MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task DelegationChenyu Wang, Yang Shu1391±412343.5%5.2+6.3May 17, 2026145Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and EfficiencyAnis Radianis1390±432552%3+39May 18, 2026146The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic SystemsYohei Nakajima1389±471546.7%5.5\-0.8May 21, 2026147A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM AgentsVasundra Srinivasan1388±402360.9%5.2+4.8May 19, 2026148STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation DiscoveryJiarui Su, Songjun Tu +21388±432161.9%6.2\-22.3May 18, 2026149RAG-based EEG-to-Text Translation Using Deep Learning and LLMsEnrico Collautti, Xiaopeng Mao +31388±421844.4%4+28May 17, 2026150Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive TrapsTanmay Asthana, Aman Saksena +11387±422445.8%6.2\-23May 17, 2026151SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM AgentsHan Li, Vibhor Malik +61387±421866.7%6.2\-23May 19, 2026152Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent DeploymentS. Bensalem, Y. Dong +61385±392548%5.5\-3.4May 18, 2026153SGR-Bench: Benchmarking Search Agents on State-Gated RetrievalNingyuan Li, Haiyang Shen +51384±481656.2%6.5\-33.6May 21, 2026154Generative Auto-Bidding with Unified Modeling and ExplorationMingming Zhang, Feiqing Zhuang +61384±422755.6%6.8\-43.6May 19, 2026155Generalization or Memorization? Brittleness Testing for Chess-Trained Language ModelsEthan Tang1383±402356.5%5+5.7May 17, 2026156Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual BottlenecksYajing Zhou, Xiangyu Kong1381±432055%3.8+27.6May 18, 2026157Planning in the LLM Era: Building for Reliability and EfficiencyMichael Katz, Harsha Kokel +21379±471546.7%4.8+9May 21, 2026158AOP-Wiki EMOD 3.0: Data Model Expansions and Content Evaluation Framework for Using Agentic AI to Improve Integration between AOPs and New Approach Methodologies (NAMs)Virginia K. Hench, J. Harry Caufield +31378±461560%4.5+15.9May 20, 2026159SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative RecommendationZaiyi Zheng, Guanghui Min +51375±392152.4%5.8\-17.2May 17, 2026160Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization TasksHaichao Miao, Zhimin Li +51373±481656.2%5+2.5May 20, 2026161Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness ResponsesYan Wang, Ziyi Guo +11370±402445.8%6.2\-28.7May 19, 2026162LACO: Adaptive Latent Communication for Collaborative DrivingTianhao Chen, Yuheng Wu +11368±481850%6.5\-38.9May 21, 2026163CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session RecordingsQixuan Hu, Shuchang Ye +61368±431947.4%5.8\-19.8May 17, 2026164EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering DesignGioele Molinari, Florian Felten +21368±402254.5%5.8\-19.8May 19, 2026165ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous DrivingQiyu Ruan, Yuxuan Wang +31367±412343.5%6.8\-49.4May 20, 2026166Scaling Observation-aware Planning in Uncertain DomainsAdrian Zvizdenco, Arthur Conrado Veiga Bosquetti +21367±422050%5+0.2May 21, 2026167Evaluating the Utility of Personal Health Records in Personalized Health AIRory Sayres, Kejia Chen +61365±411942.1%6.5\-39.7May 18, 2026168Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended GenerationGuining Cao, Jiaxin Peng +41362±441747.1%4.2+16.6May 18, 2026169AgentAtlas: Beyond Outcome Leaderboards for LLM AgentsParsa Mazaheri, Kasra Mazaheri1362±432142.9%4.8+3.4May 19, 2026170AttuneBench: A Conversation-Based Benchmark for LLM Emotional IntelligenceKate M. Lubrano, Faisal Sayed +51361±441735.3%7\-56.9May 20, 2026171Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement LearningWei Duan, Junyu Xuan +31360±422040%6.5\-41.1May 17, 2026172WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native GamesWenyu Zhang, Guoliang You +61360±441936.8%6.5\-41.1May 17, 2026173OSCToM: RL-Guided Adversarial Generation for High-Order Theory of MindSharmin Sultana Srishty, Kazi Mahathir Rahman +31359±402544%4.8+2.3May 19, 2026174Investigating Concept Alignment Using Implausible Category MembersSunayana Rane, Brenden M. Lake +11359±451450%5.8\-22.2May 20, 2026175Towards Human-Level Book-Writing CapabilityJan Zierstek, Matteo Batelic +21356±432343.5%4+17.4May 16, 2026176Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for SycophancyIshaan Kelkar, Nebras Alam +41355±432334.8%5.2\-6.1May 20, 2026177Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental ScienceYingjie Zhang, Chun Feng +21354±442055%4.8+1May 18, 2026178TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?Jieting Xiao, Yun Lin +61354±431942.1%6.2\-33.3May 18, 2026179Claw AI Lab: An Autonomous Multi-Agent Research TeamFan Wu, Cheng Chen +61353±461936.8%3.5+22.2May 21, 2026180TO-Agents: A Multi-Agent AI Pipeline for Preference-Guided Topology OptimizationIsabella A. Stewart, Hongrui Chen +11353±461643.8%5.5\-13.1May 20, 2026181When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment ApproachXinpeng Lv, Yunxin Mao +61353±441650%6.8\-53.2May 19, 2026182COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search SpaceOleksandr Yakovenko, Mahdi Mostajabdaveh +51350±412850%5.5\-14.7May 20, 2026183Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and PreemptionMert Yildiz, Pietro Spadaccino +31346±432138.1%4.5+5.3May 19, 2026184Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM AgentsXi Zhang, Meijun Gao +61346±432236.4%5.5\-15.6May 19, 2026185CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal ReasoningZhaoyue Sun, Hainiu Xu +41345±412339.1%7\-62.1May 16, 2026186Distribution-Free Uncertainty Quantification for Continuous AI Agent EvaluationYuxuan Gao, Megan Wang +11344±432045%5.8\-26.8May 19, 2026187Evaluating Cognitive Age Alignment in Interactive AI AgentsYifan Shen, Jiawen Zhang +51344±442142.9%6.2\-36.5May 18, 2026188AQuaUI: Visual Token Reduction for GUI Agents with Adaptive QuadtreesYuankai Li, Tinghui Zhu +41344±441936.8%5.5\-16May 19, 2026189POST: Prior-Observation Adversarial Learning of Spatio-Temporal Associations for Multivariate Time Series Anomaly DetectionSuofei Zhang, Yaxuan Zheng +11343±422142.9%6.8\-56.3May 18, 2026190WorkstreamBench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in FinanceThomson Yen, Julian Poeltl +61343±492128.6%6.8\-56.3May 21, 2026191Capturing LLM Capabilities via Evidence-Calibrated Query ClusteringFangzhou Wu, Sandeep Silwal +11342±442035%7.2\-67May 16, 2026192Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in PhysicsZhaoxin Yu, Nan Xu +41339±432740.7%7.2\-68May 16, 2026193Learning to Solve Compositional Geometry Routing ProblemsMingfeng Fan, Jianan Zhou +41339±412240.9%6.5\-47.6May 18, 2026194Streamlined Constraint Reasoning via CNN Pattern Recognition on Enumerated SolutionsPatrick Spracklen1339±441741.2%5.8\-28.4May 19, 2026195A Causal Argumentation Method for Explainability of Machine Learning ModelsHenry Salgado, Meagan R. Kendall +11338±472035%3.5+17.3May 20, 2026196Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical ReasoningYan Jiao, Jingran Xu +21338±431747.1%5.5\-18.1May 18, 2026197Towards Direct Evaluation of Harness Optimizers via Priority RankingKai Tzu-iunn Ong, Minseok Kang +61336±461450%7\-65May 21, 2026198A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman SpectroscopyDavid Martin-Calle, Cesar Alvarez Llamas +41335±442040%5.8\-29.9May 18, 2026199AiraXiv: An AI-Driven Open-Access Platform for Human and AI ScientistsJunshu Pan, Panzhong Lu +61335±412450%4.5+1.8May 20, 2026200ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate RankingMiaobo Hu, Shuhao Hu +61335±461631.2%5.5\-19May 21, 2026

Win-rate scores from pairwise comparisons with 95% confidence intervals. Papers compared using full-text deep analysis.