{"total":26,"rows":[{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2510.07517","title":"When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning","created":"2025-10-08","cited_by_count":21,"area":"lr"},{"id":"2511.20022","title":"WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"id":"2509.06952","title":"On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts","created":"2025-09-08","cited_by_count":5,"area":"lr"},{"id":"2511.14772","title":"Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2607.26977","title":"TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"id":"2510.05135","title":"Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2605.06444","title":"SCRuB: Social Concept Reasoning under Rubric-Based Evaluation","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.16301","title":"Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2606.01462","title":"An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models","created":"2026-05-31","cited_by_count":1,"area":"lr"},{"id":"2607.28128","title":"Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor Models","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2609.29050","title":"SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2508.02926","title":"GrandJury: A Collaborative Machine Learning Model Evaluation Protocol for Dynamic Quality Rubrics","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2601.11252","title":"Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2601.13075","title":"METIS: Mentoring Engine for Thoughtful Inquiry & Solutions","created":"2026-01-19","cited_by_count":0,"area":"lr"},{"id":"2602.17127","title":"The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI","created":"2026-02-19","cited_by_count":0,"area":"lr"},{"id":"2603.24065","title":"Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2606.29672","title":"How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2606.30653","title":"The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.19678","title":"Reference-Free Evaluation of Reasoning in Open-Ended Question Answering","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.30250","title":"Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.17644","title":"Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}