{"list":"other","total":54,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223},{"id":"2505.00212","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","created":"2025-04-30","cited_by_count":185},{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142},{"id":"2509.25370","title":"Where LLM Agents Fail and How They can Learn From Failures","created":"2025-09-29","cited_by_count":133},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124},{"id":"2406.09187","title":"GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning","created":"2024-06-13","cited_by_count":124},{"id":"2511.08325","title":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","created":"2025-11-11","cited_by_count":77},{"id":"2502.20379","title":"Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers","created":"2025-02-27","cited_by_count":62},{"id":"2407.13301","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis","created":"2024-07-18","cited_by_count":43},{"id":"2308.07758","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","created":"2023-08-15","cited_by_count":40},{"id":"2510.08049","title":"A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models","created":"2025-10-09","cited_by_count":38},{"id":"2501.16150","title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","created":"2025-01-27","cited_by_count":34},{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32},{"id":"2502.18407","title":"AgentRM: Enhancing Agent Generalization with Reward Modeling","created":"2025-02-25","cited_by_count":27},{"id":"2310.07609","title":"QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking","created":"2023-10-11","cited_by_count":26},{"id":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26},{"id":"2407.18957","title":"When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments","created":"2024-07-15","cited_by_count":26},{"id":"2501.12051","title":"MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision","created":"2025-01-21","cited_by_count":24},{"id":"2506.11474","title":"Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards","created":"2025-06-13","cited_by_count":24},{"id":"2510.13744","title":"Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math","created":"2025-10-15","cited_by_count":22},{"id":"2505.17656","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs","created":"2025-05-23","cited_by_count":18},{"id":"2508.06225","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution","created":"2025-08-08","cited_by_count":18},{"id":"2506.11887","title":"Cascaded Language Models for Cost-effective Human-AI Decision-Making","created":"2025-06-13","cited_by_count":11},{"id":"2510.10278","title":"Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models","created":"2025-10-11","cited_by_count":9},{"id":"2508.16665","title":"Trust but Verify! A Survey on Verification Design for Test-time Scaling","created":"2025-08-20","cited_by_count":8},{"id":"2412.12583","title":"Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise","created":"2024-12-17","cited_by_count":5},{"id":"2503.12532","title":"STEVE: A Step Verification Pipeline for Computer-use Agent Training","created":"2025-03-16","cited_by_count":5},{"id":"2508.19903","title":"Logical Reasoning with Outcome Reward Models for Test-Time Scaling","created":"2025-08-27","cited_by_count":3},{"id":"2510.20460","title":"Systematic Evaluation of Uncertainty Estimation Methods in Large Language Models","created":"2025-10-23","cited_by_count":3},{"id":"1810.05909","title":"Bayesian Evidence Accumulation on Social Networks","created":"2018-10-13","cited_by_count":1}],"next_cursor":null}