{"total":33,"rows":[{"id":"2407.00215","title":"LLM Critics Help Catch LLM Bugs","created":"2024-06-28","cited_by_count":147,"area":"lr"},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"area":"lr"},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2604.15149","title":"LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking","created":"2026-04-16","cited_by_count":28,"area":"lr"},{"id":"2510.01367","title":"Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort","created":"2025-10-01","cited_by_count":27,"area":"lr"},{"id":"2511.19661","title":"CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization","created":"2025-11-24","cited_by_count":26,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"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":"2505.13403","title":"MR. Judge: Multimodal Reasoner as a Judge","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2605.02909","title":"Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2601.23086","title":"Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2404.07017","title":"Improving Language Model Reasoning with Self-motivated Learning","created":"2024-04-10","cited_by_count":4,"area":"lr"},{"id":"2510.10931","title":"Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2510.11194","title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2512.11930","title":"Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2512.12576","title":"Coupled Variational Reinforcement Learning for Language Model General Reasoning","created":"2025-12-14","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2608.02442","title":"Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.05263","title":"Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.30627","title":"Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2512.05542","title":"RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs","created":"2025-12-05","cited_by_count":0,"area":"lr"},{"id":"2603.10300","title":"From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.12781","title":"Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.15445","title":"Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2609.13866","title":"The Filter Metric is Safety-Critical: Phantom Advantages in Group-Relative RL under Shaped Rewards","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2610.04928","title":"Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.06439","title":"Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.12601","title":"Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}