JoMoHa: Joint Model--Harness Optimization with Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/xudongwu-0/coevolve
Terminology
Sources
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- Counterfactual Multi-Agent Policy Gradients
- Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
- Automated Design of Agentic Systems
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- WHALE: A Simple Recipe for Joint Harness-Weight Optimization
- Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
- Meta-Harness: End-to-End Optimization of Model Harnesses
- AgentBench: Evaluating LLMs as Agents
- Self-Refine: Iterative Refinement with Self-Feedback
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reflexion: Language Agents with Verbal Reinforcement Learning
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Learning values across many orders of magnitude
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- Large Language Models as Optimizers
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis