Cover Image

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shao, Shuai, Ren, Qihan, Qian, Chen, Wei, Boyi, Guo, Dadi, Yang, Jingyi, Song, Xinhao, Zhang, Linfeng, Zhang, Weinan, Liu, Dongrui, Shao, Jing
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm
by: Guo, Dadi, et al.
Published: (2025)

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
by: Yang, Jingyi, et al.
Published: (2025)

Are Your Agents Upward Deceivers?
by: Guo, Dadi, et al.
Published: (2025)

Attributing Emergence in Million-Agent Systems
by: Tang, Ling, et al.
Published: (2026)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
by: Zhang, Boxuan, et al.
Published: (2025)

Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?
by: Guo, Dadi, et al.
Published: (2026)

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
by: Ren, Qihan, et al.
Published: (2026)

Interpreting Emergent Extreme Events in Multi-Agent Systems
by: Tang, Ling, et al.
Published: (2026)

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
by: Yang, Yingxuan, et al.
Published: (2025)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
by: Qian, Chen, et al.
Published: (2026)

MonoScale: Scaling Multi-Agent System with Monotonic Improvement
by: Shao, Shuai, et al.
Published: (2026)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
by: Ma, Qianli, et al.
Published: (2025)

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
by: Feng, Xinshun, et al.
Published: (2026)

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
by: Ren, Qibing, et al.
Published: (2025)

ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
by: Li, Yu, et al.
Published: (2026)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
by: Chen, Guanxu, et al.
Published: (2025)

HLL: Can Agents Cross Humanity's Last Line of Verification?
by: Song, Xinhao, et al.
Published: (2026)

TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?
by: Yan, Lewen, et al.
Published: (2025)

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
by: Zhang, Mingxuan, et al.
Published: (2026)

INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
by: Zhou, Yijin, et al.
Published: (2026)

REEF: Representation Encoding Fingerprints for Large Language Models
by: Zhang, Jie, et al.
Published: (2024)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
by: Liu, Dongrui, et al.
Published: (2026)

AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
by: Chen, Yulang, et al.
Published: (2026)

The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
by: Qian, Chen, et al.
Published: (2024)

Self-Consolidation for Self-Evolving Agents
by: Yu, Hongzhuo, et al.
Published: (2026)

The Better Angels of Machine Personality: How Personality Relates to LLM Safety
by: Zhang, Jie, et al.
Published: (2024)

LLM Agent for Hyper-Parameter Optimization
by: Wang, Wanzhe, et al.
Published: (2025)

Independent characterization of the elastic and the mixing parts of hydrogel osmotic pressure
by: Shao, Zefan, et al.
Published: (2023)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
by: Qian, Chen, et al.
Published: (2025)

Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?
by: Chen, Guanxu, et al.
Published: (2026)

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
by: Hu, Xuhao, et al.
Published: (2025)

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
by: Lu, Xiaoya, et al.
Published: (2025)

Self-evolving Agents with reflective and memory-augmented abilities
by: Liang, Xuechen, et al.
Published: (2024)

EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
by: Feng, Tongtong, et al.
Published: (2025)

Dynamic Risk Assessments for Offensive Cybersecurity Agents
by: Wei, Boyi, et al.
Published: (2025)

Towards the Dynamics of a DNN Learning Symbolic Interactions
by: Ren, Qihan, et al.
Published: (2024)

AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience
by: Wang, Zining, et al.
Published: (2025)

MMSkills: Towards Multimodal Skills for General Visual Agents
by: Zhang, Kangning, et al.
Published: (2026)

Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
by: Zhang, Yixiang, et al.
Published: (2025)

Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task
by: Zhang, Shao, et al.
Published: (2024)