{"total":85,"rows":[{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604,"area":"agents"},{"id":"2412.21187","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","created":"2024-12-30","cited_by_count":570,"area":"lr"},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2509.22642","title":"WoW: Towards a World omniscient World model Through Embodied Interaction","created":"2025-09-26","cited_by_count":67,"area":"wm"},{"id":"2501.09891","title":"Evolving Deeper LLM Thinking","created":"2025-01-17","cited_by_count":58,"area":"lr"},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2504.19162","title":"SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning","created":"2025-04-27","cited_by_count":42,"area":"lr"},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39,"area":"lr"},{"id":"2505.18237","title":"Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2411.17693","title":"Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats","created":"2024-11-26","cited_by_count":31,"area":"safety"},{"id":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2504.14047","title":"Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals","created":"2025-04-18","cited_by_count":18,"area":"lr"},{"id":"2409.16636","title":"Training Language Models to Win Debates with Self-Play Improves Judge Accuracy","created":"2024-09-25","cited_by_count":16,"area":"synth"},{"id":"2505.17126","title":"Conformal Language Model Reasoning with Coherent Factuality","created":"2025-05-21","cited_by_count":14,"area":"lr"},{"id":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2506.06214","title":"Can Theoretical Physics Research Benefit from Language Agents?","created":"2025-06-06","cited_by_count":9,"area":"agents"},{"id":"2510.27338","title":"Reasoning Models Sometimes Output Illegible Chains of Thought","created":"2025-10-31","cited_by_count":9,"area":"lr"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2506.22920","title":"Improving Rationality in the Reasoning Process of Language Models through Self-playing Game","created":"2025-06-28","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2410.13852","title":"Retrospective Learning from Interactions","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6,"area":"lr"},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2606.00424","title":"Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5,"area":"alignment"},{"id":"2603.20508","title":"Measuring Weak-to-Strong Legibility of Reasoning Models","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2508.01969","title":"Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2512.10739","title":"Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving","created":"2025-12-11","cited_by_count":4,"area":"lr"},{"id":"2605.20531","title":"Pseudo-Formalization for Automatic Proof Verification","created":"2026-05-19","cited_by_count":4,"area":"lr"},{"id":"2410.01064","title":"Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2410.10596","title":"Overcoming classic challenges for artificial neural networks by providing incentives and practice","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2602.10153","title":"Basic Legibility Protocols Improve Trusted Monitoring","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2607.18966","title":"Measuring Reward-Seeking via Contrastive Belief Updates","created":"2026-07-21","cited_by_count":3,"area":"alignment"},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2510.13982","title":"Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations","created":"2025-10-15","cited_by_count":2,"area":"agents"},{"id":"2510.14913","title":"Budget-aware Test-time Scaling via Discriminative Verification","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2602.00127","title":"ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.09000","title":"iGRPO: Self-Feedback-Driven LLM Reasoning","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2605.14163","title":"Agentic Systems as Boosting Weak Reasoning Models","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2605.30290","title":"Self-Trained Verification for Training- and Test-Time Self-Improvement","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.10684","title":"Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals","created":"2026-06-09","cited_by_count":2,"area":"agents"},{"id":"2607.03561","title":"How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2608.21027","title":"Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2510.09278","title":"CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.15772","title":"Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2602.23248","title":"Mitigating Legibility Tax with Decoupled Prover-Verifier Games","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.27483","title":"Debate Helps Weak Judges Reward Stronger Models","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.23802","title":"From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2507.07532","title":"Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.03396","title":"Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis","created":"2025-08-05","cited_by_count":0,"area":"lr"},{"id":"2604.04418","title":"Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.10810","title":"Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.27914","title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","created":"2026-05-27","cited_by_count":0,"area":"synth"},{"id":"2605.28807","title":"Calibrating Conservatism for Scalable Oversight","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2606.31748","title":"Addressing Over-Refusal in LLMs with Competing Rewards","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2607.01223","title":"Theoria: Rewrite-Acceptability Verification over Informal Reasoning States","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.07690","title":"Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.20852","title":"Code Monitor Red Teaming for Public-Test-Passing Code","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2608.17051","title":"Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.09776","title":"Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled Reward","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.24895","title":"Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31186","title":"Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32061","title":"Contract monitoring: governing AI via separation of powers","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32361","title":"Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33773","title":"Learning Strategies to Break Judges","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01514","title":"How the Audit Rule Shapes Faithful Factor Explanations in LLMs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02557","title":"How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.17697","title":"LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}