{"total":99,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2509.05396","title":"Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate","created":"2025-09-05","cited_by_count":66,"area":"lr"},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25,"area":null},{"id":"2601.20245","title":"How AI Impacts Skill Formation","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"area":"safety"},{"id":"2504.04785","title":"Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors","created":"2025-04-07","cited_by_count":22,"area":"agents"},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2505.24671","title":"Multiple LLM Agents Debate for Equitable Cultural Alignment","created":"2025-05-30","cited_by_count":21,"area":"agents"},{"id":"2511.13288","title":"Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO","created":"2025-11-17","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":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2411.01344","title":"Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent","created":"2024-11-02","cited_by_count":14,"area":"agents"},{"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":"2504.00374","title":"When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)","created":"2025-04-01","cited_by_count":12,"area":"agents"},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2507.14295","title":"A Simple \"Try Again\" Can Elicit Multi-Turn LLM Reasoning","created":"2025-07-18","cited_by_count":11,"area":"lr"},{"id":"2502.11244","title":"Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment","created":"2025-02-16","cited_by_count":10,"area":"alignment"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2607.05904","title":"More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges","created":"2026-07-07","cited_by_count":10,"area":"alignment"},{"id":"2603.07972","title":"Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning","created":"2026-03-09","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8,"area":"agents"},{"id":"2502.18018","title":"Verdict: A Library for Scaling Judge-Time Compute","created":"2025-02-25","cited_by_count":7,"area":null},{"id":"2502.19414","title":"Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation","created":"2025-02-26","cited_by_count":7,"area":"lr"},{"id":"2601.03775","title":"Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations","created":"2026-01-07","cited_by_count":7,"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":"2503.04736","title":"Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2601.17152","title":"Dynamic Role Assignment for Multi-Agent Debate","created":"2026-01-23","cited_by_count":5,"area":"mllm"},{"id":"2605.29192","title":"ReasonOps: Operator Segmentation for LLM Reasoning Traces","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4,"area":"alignment"},{"id":"2510.13912","title":"AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2510.20963","title":"When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2608.17776","title":"Debate Training Reduces Reward Hacking in RLAIF","created":"2026-08-18","cited_by_count":4,"area":"alignment"},{"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":"2504.03731","title":"A Benchmark for Scalable Oversight Protocols","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2509.15568","title":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","created":"2025-09-19","cited_by_count":3,"area":"synth"},{"id":"2510.26518","title":"Human-AI Complementarity: A Goal for Amplified Oversight","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2510.26752","title":"The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"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":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2510.04488","title":"Multi-Agent Collaborative Intelligence: Dual-Dial Control for Reliable LLM Reasoning","created":"2025-10-06","cited_by_count":2,"area":"lr"},{"id":"2605.01704","title":"The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning","created":"2026-05-03","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":"2607.15388","title":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","created":"2026-07-16","cited_by_count":2,"area":"lr"},{"id":"2502.18531","title":"Enhancing Hepatopathy Clinical Trial Efficiency: A Secure, Large Language Model-Powered Pre-Screening Pipeline","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2601.13566","title":"Self-Improvement as Coherence Optimization: A Theoretical Account","created":"2026-01-20","cited_by_count":1,"area":"synth"},{"id":"2602.14307","title":"Benchmarking at the Edge of Comprehension","created":"2026-02-15","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":"2606.11998","title":"Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.15029","title":"Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.27958","title":"$\\Sigma$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"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":"2407.12877","title":"ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models","created":"2024-07-16","cited_by_count":0,"area":"lr"},{"id":"2505.14627","title":"Debating for Better Reasoning: An Unsupervised Multimodal Approach","created":"2025-05-20","cited_by_count":0,"area":"lr"},{"id":"2510.05909","title":"Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2604.10389","title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","created":"2026-04-12","cited_by_count":0,"area":"rag"},{"id":"2605.04356","title":"Efficiently Aligning Language Models with Online Natural Language Feedback","created":"2026-05-05","cited_by_count":0,"area":"alignment"},{"id":"2605.07021","title":"Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.08321","title":"LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.28807","title":"Calibrating Conservatism for Scalable Oversight","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.14629","title":"When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.01251","title":"Collaborative Disagreement Resolution for Scalable Oversight","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.01584","title":"EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.20852","title":"Code Monitor Red Teaming for Public-Test-Passing Code","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2608.19216","title":"Bounded Sovereignty and the Control Tax: Pricing AI Oversight When the Deployer Does Not Own the Model","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20392","title":"Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.24807","title":"Automatic Model Card Generation Using an LLM","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00652","title":"Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary Search","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.05088","title":"Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.22497","title":"The Wisdom of Artificial Deliberative Crowds","created":"2026-09-18","cited_by_count":0,"area":null},{"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":"2609.32361","title":"Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.35875","title":"Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.36049","title":"Improving scalable oversight with co-trained monitors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00111","title":"A Low Grounding Score Is Not an Ungrounded Judge: Identifying the Perceptibility Confound in Multimodal Oversight","created":"2026-09-09","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":"2610.08540","title":"Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements","created":"2026-10-06","cited_by_count":0,"area":"safety"},{"id":"2610.15778","title":"Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.15938","title":"The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}