{"total":77,"rows":[{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686,"area":"alignment"},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526,"area":"lr"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2602.06820","title":"ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training","created":"2026-02-06","cited_by_count":32,"area":null},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2503.21961","title":"Entropy-Gated Branching for Efficient Test-Time Reasoning","created":"2025-03-27","cited_by_count":22,"area":"lr"},{"id":"2501.10069","title":"A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks","created":"2025-01-17","cited_by_count":21,"area":"lr"},{"id":"2503.13551","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","created":"2025-03-16","cited_by_count":18,"area":"lr"},{"id":"2505.22338","title":"Text2Grad: Reinforcement Learning from Natural Language Feedback","created":"2025-05-28","cited_by_count":18,"area":"alignment"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"area":"alignment"},{"id":"2511.01934","title":"Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch","created":"2025-11-02","cited_by_count":17,"area":"agents"},{"id":"2406.01364","title":"BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2502.09192","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","created":"2025-02-13","cited_by_count":14,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2412.17149","title":"A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops","created":"2024-12-22","cited_by_count":13,"area":"agents"},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2506.04039","title":"Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization","created":"2025-06-04","cited_by_count":10,"area":"mllm"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2505.17455","title":"Towards Evaluating Proactive Risk Awareness of Multimodal Language Models","created":"2025-05-23","cited_by_count":6,"area":"mllm"},{"id":"2507.18742","title":"Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement","created":"2025-07-24","cited_by_count":6,"area":"alignment"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2403.00188","title":"Impact of Decentralized Learning on Player Utilities in Stackelberg Games","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2508.04216","title":"Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction","created":"2025-08-06","cited_by_count":5,"area":"lr"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2602.03806","title":"Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation","created":"2026-02-03","cited_by_count":4,"area":"offlinerl"},{"id":"2501.06271","title":"Large Language Models for Bioinformatics","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2502.14171","title":"Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction","created":"2025-02-20","cited_by_count":3,"area":"agents"},{"id":"2507.08249","title":"Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2605.01771","title":"The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't","created":"2026-05-03","cited_by_count":3,"area":null},{"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":"2503.08117","title":"Convergence Dynamics and Stabilization Strategies of Co-Evolving Generative Models","created":"2025-03-11","cited_by_count":2,"area":"synth"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2509.23095","title":"Causally-Enhanced Reinforcement Policy Optimization","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2601.05960","title":"Distilling Feedback into Memory-as-a-Tool","created":"2026-01-09","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":"2607.17641","title":"Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents","created":"2026-07-20","cited_by_count":2,"area":"lr"},{"id":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","cited_by_count":2,"area":"agents"},{"id":"2509.22735","title":"Regulating the Agency of LLM-based Agents","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2510.12249","title":"Optimal Regularization for Performative Learning","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.26200","title":"Workflow Closure Is Not Scientific Closure in Auto-Research Systems","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.09766","title":"Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2602.00497","title":"Culturally-Grounded Governance for Multilingual Language Models: Rights, Data Boundaries, and Accountable AI Design","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.04237","title":"Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2605.27375","title":"LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2606.03238","title":"When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2608.05560","title":"From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs","created":"2026-08-06","cited_by_count":0,"area":"safety"},{"id":"2608.05990","title":"OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.14795","title":"Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.12039","title":"Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.25848","title":"Optimizing the Score, Losing Sight of the Task: Reward Hacking Across Weights, Selection, and Prompts","created":"2026-09-22","cited_by_count":0,"area":"alignment"},{"id":"2609.30266","title":"LLM Agents Can Easily Tamper With Their Own Traces","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.00707","title":"Initialization Improves LLM-Driven Discovery","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03631","title":"NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04364","title":"A Bird's-Eye View of Iterative Reward Design","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.12822","title":"Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems","created":"2026-10-09","cited_by_count":0,"area":"alignment"},{"id":"2610.13008","title":"Provenance-Aware Belief Updating in Human-AI Feedback Loops","created":"2026-10-09","cited_by_count":0,"area":null},{"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}