Mixture of Self-Improving Branches For Agent Harness Optimization
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/SWE-agent/mini-swe-agent
Terminology
Sources
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
- Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
- DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
- DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution
- Self-Evolving Multi-Agent Systems via Decentralized Memory
- Automated Design of Agentic Systems
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Meta-Harness: End-to-End Optimization of Model Harnesses
- AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- Illuminating search spaces by mapping elites
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- RouteLLM: Learning to Route LLMs with Preference Data
- HARBOR: Automated Harness Optimization
- Rethinking the Evaluation of Harness Evolution for Agents
- Token-Level LLM Collaboration via FusionRoute
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
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