SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

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 competence. In this paper, we introduce HarnessEvolve,

Read original source ↗ Open in workspace

recordType

paper

region

Global