# Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents arXiv: https://arxiv.org/abs/2609.11677 · HTML: https://mlsanity.com/paper/2609.11677/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 31 of its 33 references that are in the map. - First posted on arXiv 10 Sep 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 30 of 31) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023) - [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023) - [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025) - [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024) - [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024) - [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025) - [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026) - [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025) - [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025) - [Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine](https://mlsanity.com/paper/2510.21614/) (2025) - [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026) - [MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning](https://mlsanity.com/paper/2409.12147/) (2024) - [Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning](https://mlsanity.com/paper/2502.11799/) (2025) - [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026) - [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026) - [Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents](https://mlsanity.com/paper/2605.22166/) (2026) - [HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems](https://mlsanity.com/paper/2606.01779/) (2026) - [COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context](https://mlsanity.com/paper/2510.08790/) (2025) - [HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses](https://mlsanity.com/paper/2608.01918/) (2026) - [MemoHarness: Agent Harnesses That Learn from Experience](https://mlsanity.com/paper/2607.14159/) (2026) - [Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories](https://mlsanity.com/paper/2608.02276/) (2026) - [Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable](https://mlsanity.com/paper/2607.13285/) (2026) - [HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution](https://mlsanity.com/paper/2609.00829/) (2026) - [OpenForgeRL: Train Harness-native Agents in Any Environment](https://mlsanity.com/paper/2607.21557/) (2026) - [Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification](https://mlsanity.com/paper/2608.27311/) (2026) - [Engineering Pitfalls in AI Coding Tools: An Empirical Study of Bugs in Claude Code, Codex, and Gemini CLI](https://mlsanity.com/paper/2603.20847/) (2026) - [SHE: Trajectory-driven Safety Harness Evolution for LLM Agents](https://mlsanity.com/paper/2608.09885/) (2026) - [What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection](https://mlsanity.com/paper/2609.05198/) (2026) ## Built on by (most cited first, 3 of 3) - [Harness Learning Enables Generalizable Test-Time Adaptation](https://mlsanity.com/paper/2609.35738/) (2026) - [Harness Evolution Hits a Ceiling: When Weight Training Should Begin](https://mlsanity.com/paper/2610.11655/) (2026) - [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026) ## Abstract (arXiv) 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 failure-driven approaches often treat observed agent failures as direct evidence for harness modification. A key challenge in failure-driven harness evolution is that observed failures can reflect either limitations of the underlying model or systematic deficiencies of the harness. Directly optimizing against individual failures can therefore induce model-specific accommodation and impair generalization across tasks and models. We study whether failure evidence accumulated across task instances can provide a more reliable signal for harness training. Our key insight is that failures recurring across distinct tasks provide stronger inductive evidence for systematic harness deficiencies than isolated failures. Based on this insight, we propose Ecdysis, which aggregates failure evidence across task instances before promoting recurring failure patterns into persistent harness evolution, biasing evolution toward repairs that are more likely to generalize beyond individual model behaviors. Ecdysis further employs collaborative failure analysis to refine modification specifications, trading additional evolution-time reasoning for improved modification quality. Across multiple LLMs and benchmarks, Ecdysis improves the reasoning accuracy of evolved harnesses by 18.56% over existing harness evolution while achieving up to 1.84x faster harness training. Ecdysis also enables more data-efficient training. Fine-grained analysis shows that Ecdysis reduces model-specific accommodation during evolution, while the resulting harnesses exhibit stronger cross-LLM generalization and lower inference-time token consumption.