Causal Improvement Graph for Agentic Harness Optimization
cs.CL
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/openclaw/openclaw
Sources
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Living-Harness Is an Interactive-Agent Evolver
- Effective Harness Engineering for Algorithm Discovery with Coding Agents
- Kimi K3: Open Frontier Intelligence
- Recursive Harness Self-Improvement
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- AutoHarness: improving LLM agents by automatically synthesizing a code harness
- AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
- EviGraph: Evidence-Guided Autonomous Research Agents
- Rethinking the Evaluation of Harness Evolution for Agents
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
- Self-Harness: Harnesses That Improve Themselves
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Hyperagents
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering