Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
cs.AI, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/SWE-agent/mini-swe-agent
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Executable Code Actions Elicit Better LLM Agents
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- Self-Harness: Harnesses That Improve Themselves
- Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
- Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
- ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
- HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
- HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
- Self-Evolving Coding Agents
- Rethinking the Evaluation of Harness Evolution for Agents
- HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems