{"total":18,"rows":[{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2604.11806","title":"Detecting Safety Violations Across Many Agent Traces","created":"2026-04-13","cited_by_count":14,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2604.11072","title":"Hodoscope: Unsupervised Monitoring for AI Misbehaviors","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2607.21763","title":"Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2605.21401","title":"Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.12426","title":"Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.38411","title":"A Competing-Hazards Systematization of Loss of Control in Autonomous Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.09426","title":"RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17016","title":"ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17370","title":"HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}