SOURCE-LINKED INTELLIGENCE

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for optimizing agent execution. Existing harness evolution methods typically rely on iterative search, repeatedly evaluating and revising candidate harnesses based on execution feedback from task instances. While this paradigm enables continuous harness optimization, it incurs substantial time overhead due to repeated agent executions and code modifications, and may overfit to observed tasks and specific failure patterns, resulting in degraded general

Read original source ↗ Open in workspace

recordType

paper

region

Global