HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution

Key takeaways

• arXiv:2609.00829v1 Announce Type: cross Abstract: Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback.
• This paradigm, however, is hampered by three challenges: \textit{credit assignment failure}, where terminal success/failure feedback makes it ambiguous which step caused the error; \textit{shortcut learning}, where agents memorize task-specific patterns rather than acquire generalizable capabilities; and \textit{catastrophic forgetting}, where unguarded updates degrade previously acquired comp