Cover Image

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Minhua, Wu, Juncheng, Wang, Zijun, Shi, Zhan, Sang, Yisi, He, Bing, Liu, Zewen, Wei, Tianxin, Wu, Zongyu, Zhang, Zhiwei, Wang, Dakuo, Zhang, Xiang, Dumoulin, Benoit, Xie, Cihang, Zhou, Yuyin, Wang, Suhang, Lu, Hanqing
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
by: Liu, Zewen, et al.
Published: (2026)

Position: Agentic Evolution is the Path to Evolving LLMs
by: Lin, Minhua, et al.
Published: (2026)

Robustness Inspired Graph Backdoor Defense
by: Zhang, Zhiwei, et al.
Published: (2024)

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
by: Wu, Zongyu, et al.
Published: (2025)

Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
by: Lin, Minhua, et al.
Published: (2024)

LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
by: Xu, Junjie, et al.
Published: (2024)

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
by: Wu, Juncheng, et al.
Published: (2026)

Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
by: Zhang, Zhiwei, et al.
Published: (2024)

MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
by: Lin, Minhua, et al.
Published: (2026)

Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs
by: Wang, Yilong, et al.
Published: (2025)

Universal Prompt Optimizer for Safe Text-to-Image Generation
by: Wu, Zongyu, et al.
Published: (2024)

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
by: Lin, Minhua, et al.
Published: (2024)

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
by: Lu, Yuxuan, et al.
Published: (2026)

PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection
by: Dai, Enyan, et al.
Published: (2024)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
by: Wu, Juncheng, et al.
Published: (2026)

RewardHarness: Self-Evolving Agentic Post-Training
by: Zhang, Yuxuan, et al.
Published: (2026)

GPR: Empowering Generation with Graph-Pretrained Retriever
by: Wang, Xiaochen, et al.
Published: (2025)

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs
by: Wu, Xueqing, et al.
Published: (2024)

AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation
by: Zhang, Xiechi, et al.
Published: (2025)

Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays
by: Kim, Harim, et al.
Published: (2025)

MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
by: Wang, Hanqing, et al.
Published: (2024)

A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
by: Lin, Minhua, et al.
Published: (2025)

Catastrophic Failure of LLM Unlearning via Quantization
by: Zhang, Zhiwei, et al.
Published: (2024)

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
by: Chen, Hardy, et al.
Published: (2026)

LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models
by: Wu, Zongyu, et al.
Published: (2025)

Harnessing Photonics for Machine Intelligence
by: Zhu, Hanqing, et al.
Published: (2026)

Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
by: Hu, Juncheng, et al.
Published: (2026)

Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains
by: Wu, Juncheng, et al.
Published: (2025)

Harnessing Agentic Evolution
by: Zhang, Jiayi, et al.
Published: (2026)

Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?
by: Zhang, Xianren, et al.
Published: (2024)

Counterfactual Learning on Graphs: A Survey
by: Guo, Zhimeng, et al.
Published: (2023)

DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
by: Wu, Juncheng, et al.
Published: (2024)

Harnessing Catalytic RNA Circuits for Construction of Artificial Signaling Pathways in Mammalian Cells
by: Chao‐Qun Wu, et al.
Published: (2024)

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
by: Wang, Zijun, et al.
Published: (2025)

Harnessing from Nature – Evolving Potential of Antimicrobial Peptide
by: Songhan Liu, et al.
Published: (2025)

Harnessing Water Molecules for Strong Underwater Adhesion
by: Biaolong Ma, et al.
Published: (2026)

Unlearning Inversion Attacks for Graph Neural Networks
by: Zhang, Jiahao, et al.
Published: (2025)

Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
by: Wang, Chengcheng, et al.
Published: (2026)

Code as Agent Harness
by: Ning, Xuying, et al.
Published: (2026)

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
by: Wang, Zijun, et al.
Published: (2026)