{"total":65,"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":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31,"area":"agents"},{"id":"2511.21654","title":"EvilGenie: A Reward Hacking Benchmark","created":"2025-11-26","cited_by_count":28,"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":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"area":"alignment"},{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16,"area":"agents"},{"id":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"area":"lr"},{"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":"2605.20744","title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale","created":"2026-05-20","cited_by_count":10,"area":"alignment"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2603.25111","title":"SEVerA: Verified Synthesis of Self-Evolving Agents","created":"2026-03-26","cited_by_count":8,"area":"agents"},{"id":"2606.16613","title":"CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies","created":"2026-06-15","cited_by_count":8,"area":"agents"},{"id":"2601.07663","title":"Reasoning Models Will Sometimes Lie About Their Reasoning","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"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":"2608.30724","title":"BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks","created":"2026-08-31","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"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":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2606.07379","title":"Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2607.09709","title":"The Verifier is the Curriculum: Precision Sets the Return on Search in Code Self-Distillation","created":"2026-06-23","cited_by_count":3,"area":"distill"},{"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":"2608.16801","title":"When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2605.17453","title":"Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"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":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","cited_by_count":2,"area":"agents"},{"id":"2609.28614","title":"Reward Hacking Challenges Oversight of Autonomous Research Agents","created":"2026-09-23","cited_by_count":2,"area":"agents"},{"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":"2608.13760","title":"Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2609.36308","title":"CheatBench: Measuring Reward Gaming in AI Agents","created":"2026-09-28","cited_by_count":1,"area":"alignment"},{"id":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.10947","title":"RH-Detect: A Unified Benchmark for Reward Hacking Detection","created":"2026-10-07","cited_by_count":1,"area":"alignment"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.18064","title":"Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"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":"2608.22103","title":"Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"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":"2609.14998","title":"Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking","created":"2026-09-14","cited_by_count":0,"area":"alignment"},{"id":"2609.15494","title":"The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18996","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30217","title":"Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure","created":"2026-09-24","cited_by_count":0,"area":"safety"},{"id":"2609.35677","title":"Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.37310","title":"AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"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":"2609.39533","title":"CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04646","title":"SEIS: Self-Evolving Inference Systems","created":"2026-10-03","cited_by_count":0,"area":"synth"},{"id":"2610.04915","title":"Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.06576","title":"Before Agent Tells The Lie: Has Deception Already Been Represented?","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.09159","title":"SpecGuard: Proving a Task Is Broken Before the Agent Cheats","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"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":"2610.11678","title":"TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"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":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"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}