{"total":14,"rows":[{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2501.00430","title":"Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents","created":"2024-12-31","cited_by_count":15,"area":"lr"},{"id":"2505.08827","title":"RLSR: Reinforcement Learning from Self Reward","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2602.04649","title":"Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models","created":"2026-02-04","cited_by_count":11,"area":"lr"},{"id":"2505.03439","title":"The Steganographic Potentials of Language Models","created":"2025-05-06","cited_by_count":10,"area":"lr"},{"id":"2405.12933","title":"Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs","created":"2024-05-21","cited_by_count":8,"area":"lr"},{"id":"2412.03904","title":"MISR: Measuring Instrumental Self-Reasoning in Frontier Models","created":"2024-12-05","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2606.05625","title":"Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2601.00830","title":"Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2609.34056","title":"Steering Language Model Goals with Value Transplant","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36254","title":"Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}