HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/anthropics/claude-code
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- MemGPT: Towards LLMs as Operating Systems
- A Self-Improving Coding Agent
- Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
- HARBOR: Automated Harness Optimization
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- ReAct: Synergizing Reasoning and Acting in Language Models
- TextGrad: Automatic "Differentiation" via Text
- G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
- Multi-agent Architecture Search via Agentic Supernet
- Self-Harness: Harnesses That Improve Themselves
- Hyperagents
- HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
- DarwinX: Evolving Agent Harnesses Through Natural Selection
- Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents