{"total":62,"rows":[{"id":"2602.15654","title":"Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections","created":"2026-02-17","cited_by_count":48,"area":"agents"},{"id":"2604.04759","title":"Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw","created":"2026-04-06","cited_by_count":20,"area":"agents"},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16,"area":"agents"},{"id":"2605.13527","title":"MMSkills: Towards Multimodal Skills for General Visual Agents","created":"2026-05-13","cited_by_count":16,"area":null},{"id":"2605.18930","title":"OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences","created":"2026-05-18","cited_by_count":14,"area":"agents"},{"id":"2601.15075","title":"The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution","created":"2026-01-21","cited_by_count":11,"area":"agents"},{"id":"2605.05583","title":"Belief Memory: Agent Memory Under Partial Observability","created":"2026-05-07","cited_by_count":11,"area":"agents"},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","cited_by_count":11,"area":"agents"},{"id":"2602.03224","title":"TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking","created":"2026-02-03","cited_by_count":10,"area":"agents"},{"id":"2605.10663","title":"Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents","created":"2026-05-11","cited_by_count":9,"area":"agents"},{"id":"2608.24876","title":"Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses","created":"2026-08-25","cited_by_count":9,"area":"agents"},{"id":"2602.03100","title":"Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"id":"2605.11882","title":"On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment","created":"2026-05-12","cited_by_count":8,"area":"agents"},{"id":"2605.02900","title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","created":"2026-03-28","cited_by_count":7,"area":"safety"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2605.09315","title":"Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation","created":"2026-05-10","cited_by_count":6,"area":"agents"},{"id":"2601.09465","title":"EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines","created":"2026-01-14","cited_by_count":5,"area":"agents"},{"id":"2601.23219","title":"MonoScale: Scaling Multi-Agent System with Monotonic Improvement","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2607.23586","title":"Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents","created":"2026-07-26","cited_by_count":5,"area":null},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2605.05704","title":"SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2608.00155","title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","created":"2026-07-31","cited_by_count":4,"area":"agents"},{"id":"2609.00069","title":"Auditing Harness Tampering in Self-Improving Agents","created":"2026-08-30","cited_by_count":4,"area":"synth"},{"id":"2602.10429","title":"AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles","created":"2026-02-11","cited_by_count":3,"area":"agents"},{"id":"2605.20086","title":"What Do Evolutionary Coding Agents Evolve?","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2605.23019","title":"PACE: Two-Timescale Self-Evolution for Small Language Model Agents","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2608.12851","title":"Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2609.11677","title":"Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2604.24919","title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","created":"2026-04-27","cited_by_count":2,"area":"agents"},{"id":"2605.22505","title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"area":"synth"},{"id":"2609.06396","title":"MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves","created":"2026-09-06","cited_by_count":2,"area":null},{"id":"2601.13981","title":"VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation","created":"2026-01-20","cited_by_count":1,"area":"agents"},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2604.03400","title":"Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2604.15774","title":"MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents","created":"2026-04-17","cited_by_count":1,"area":"agents"},{"id":"2606.06114","title":"ANCHOR: An External LLM-Driven Supervisory Module Facilitating Healthy Evolution in Self-Evolving Systems","created":"2026-06-04","cited_by_count":1,"area":"synth"},{"id":"2607.05163","title":"Open Problems in AI Incident Governance","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2610.04756","title":"When Is Enough Enough in Self-Evolving LLM Systems?","created":"2026-10-03","cited_by_count":1,"area":"synth"},{"id":"2511.02979","title":"Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2605.16309","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2607.05165","title":"Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.10878","title":"LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.05158","title":"Safe Evolution with Circuit Anchors","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2608.17684","title":"Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.21544","title":"Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.17817","title":"Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.31186","title":"Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33123","title":"Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33524","title":"EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33910","title":"When Consent Outlives Context: Residual Authority Replay in Long-Lived Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35596","title":"SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39473","title":"Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00650","title":"Self-Evolving Coding Rules for AI Coding Agents","created":"2026-09-30","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":"2610.06576","title":"Before Agent Tells The Lie: Has Deception Already Been Represented?","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.12651","title":"SynAct: Synergistic Active Feedback Learning for LLM Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12813","title":"VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15244","title":"EvolvAttack: Backdooring self Evolving VLM Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.18813","title":"Self-Evolving Agent Harness","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}