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

arXiv:2609.11677 · cs.SE, cs.AI · Submitted 2026-09-10 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-09-10

Updated: 2026-09-20

Code: https://github.com/cuiyu-ai/Ecdysis

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 15× in this paper · explained in 1 episode
• Generalization — 14× in this paper · explained in 13 episodes
• Adaptation — 9× in this paper · explained in 1 episode
• Aggregation — 9× in this paper · explained in 1 episode
• Failure-Driven Collaborative Refinement — 6× in this paper
• Benchmark — 5× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• On-Policy Distillation — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Task Planning — 1× in this paper · explained in 2 episodes

Sources

• Recursive Harness Self-Improvement
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
• Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
• HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
• Self-Harness: Harnesses That Improve Themselves
• OpenForgeRL: Train Harness-native Agents in Any Environment
• MemoHarness: Agent Harnesses That Learn from Experience
• Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
• Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
• Qwen3 Technical Report
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties