{"total":32,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2607.01071","title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","created":"2026-07-01","cited_by_count":12,"area":"agents"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2509.25302","title":"Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2502.16810","title":"AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting","created":"2025-02-24","cited_by_count":6,"area":"agents"},{"id":"2408.01725","title":"The Drama Machine: Simulating Character Development with LLM Agents","created":"2024-08-03","cited_by_count":5,"area":"agents"},{"id":"2607.00038","title":"Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting","created":"2026-06-28","cited_by_count":5,"area":"agents"},{"id":"2606.15385","title":"Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds","created":"2026-06-13","cited_by_count":4,"area":"agents"},{"id":"2604.28093","title":"What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2608.12841","title":"AQuA: Recursively Self-Improving Quantitative Trading Research Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2604.13107","title":"Can Coding Agents Be General Agents?","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2604.20200","title":"Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows","created":"2026-04-22","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","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":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2608.06811","title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"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":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2606.08500","title":"Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey","created":"2026-06-07","cited_by_count":0,"area":"agents"},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.00058","title":"CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"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":"2609.30266","title":"LLM Agents Can Easily Tamper With Their Own Traces","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"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":"2610.04083","title":"Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.10942","title":"StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.17724","title":"Evidence-First Agentic Verification","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}