The papers

Most central to this idea first, not most recent.

• Industrycs.AI

  Research agent improves itself through seven successive code rewrites

  Weco AI · Sept 2026

• Independentcs.AI

  Closed-loop development improves mobile agents across planning and tool use

  Sept 2026

• Independentcs.SE

  LLMs can build agent harnesses, but improvements transfer poorly

  Sept 2026

• Research Labcs.SE

  Cross-task failure diagnosis makes LLM agent harness training faster

  Chengdu Institute of Computer Applications, Chinese Academy of Sciences, University of Chinese Academy of Sciences · Sept 2026

• Chinese Techcs.SE

  Self-evolving harness turns general AI agents into stronger RCA specialists

  The Chinese University of Hong Kong, Individual Researcher · Aug 2026

• Top Universitycs.CL

  Generating Agent Harnesses on Demand Improves Models Across Benchmarks

  LV-NUS Lab · Aug 2026

• Top Universitycs.AI

  Evolved agent harnesses lift enterprise performance without retraining models

  ServiceNow, Mila · Aug 2026

• Top Universitycs.AI

  Behavior-aware checks make agent harness evolution cheaper and more reliable

  Fudan University, Shanghai Key Laboratory of Data Science · Aug 2026

• Top Universitycs.CL

  Adaptive task selection cuts the cost of optimizing LLM agent harnesses

  The University of Tokyo · Aug 2026

• Top Universitycs.AIcode

  Re-evaluation shows harness evolution for agents may not outperform simple test-time scaling

  Allen Institute for AI, University of Washington · July 2026

• Chinese Techcs.AIcode

  Evolutionary training harness co-evolves with LLM policies for RL

  Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Tongyi Lab , Alibaba Group · June 2026

• Big Techcs.AI

  Self-supervised method improves agent harnesses using past trajectories

  City University of Hong Kong, Microsoft Research Asia · June 2026

• Top Universitycs.RO

  Visual action rehearsal helps language models control robot manipulation

  HKUST(GZ), CUHK · Sept 2026

• Chinese Techcs.AI

  Self-improving context programs help frozen models understand long videos

  Tencent · Aug 2026

• Chinese Techcs.AI

  Restructuring agent environments improves performance on noisy, evolving tasks

  Shanghai Jiao Tong University, Theseus Labs · Sept 2026

• Independentcs.CL

  Models struggle to improve themselves from vague capability goals

  Sept 2026

• Industrycs.AI

  Layered agent harnesses improve software over repeated autonomous development cycles

  Shanghai Artificial Intelligence Laboratory · Sept 2026

• Big Techcs.AI

  Skill evolution improves agent performance in image generation workflows

  University of Pennsylvania, Nvidia · July 2026