Knowledge in the Harness, Reliability in the Weights: Teacher-Free Co-Evolution of an LLM Agent
cs.CL, cs.AI, cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/Brightendata/knowledge-in-the-harness
Terminology
Sources
- CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
- Harness-Delta Attribution: Dissecting Gains From Harness Evolution
- Living-Harness Is an Interactive-Agent Evolver
- From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
- Gemma 4 Technical Report
- SIA: Self Improving AI with Harness & Weight Updates
- How Many Instructions Can LLMs Follow at Once?
- SkillAdam: Stable and Efficient Skill Evolution for Agents
- Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Harness Evolution Hits a Ceiling: When Weight Training Should Begin
- Rethinking the Evaluation of Harness Evolution for Agents
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- The Invisible Leash: Why RLVR May or May Not Escape Its Origin
- SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
- Evo squared: Evolving the Evolver through Weight-Harness Co-Evolution
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data