Paper · Tools and harness
Training the Whole Agent, Not Just the Model
HarnessAdapt-RL trains a policy and adapts its execution harness simultaneously during reinforcement learning by using teacher models to generate skills and evolve tools based on training trajectories.
The loop
Teacher models evolve an agent's harness and tools during reinforcement learning based on its trajectories. The policy trains with this adapted harness, improving its coding performance and generating new trajectories that guide further adaptation.
- Teacher models evolve tools and skills
- Policy trains with adapted harness
- Policy generates new trajectories
- Trajectories guide further harness adaptation
- Teacher models evolve tools and skills
- Policy trains with adapted harness
- Policy generates new trajectories
- Trajectories guide further harness adaptation
↻ The improved system does the next round, and the loop turns again.
Why it is a road to recursion
Simultaneously updating the policy and its execution harness prevents the agent from being bottlenecked by fixed tools during reinforcement learning.
Evidence
Improves pass@1 over GRPO by 9.8 to 12.6 percentage points on SWE-bench datasets.
harness-evolutionreinforcement-learningcoding-agents
Related loops
More tools and harness →
ScholarEvolve
- Research agent writes harness mutation blueprints
- Coding agent implements harness module changes
- Winning harness becomes the new champion
- New champion harness runs further generations
- repeat
Tools and harnessYang et al. (UC Santa Barbara, Microsoft) · 2026
Self-Evolving Coding Agents via Harness-Policy Optimization
- Policy analyzes its own failures
- Proposes new harness candidates
- Policy trains via RL on new harness
- Successor policy tackles harder tasks
- repeat
Tools and harnessZhepei Wei et al. · 2026
Cortex
- Cortex tests harness changes
- evaluates new skills and rules
- retains only net-gain modifications
- updates the agent's harness
- repeat
Tools and harnessSamuele Giampieri · 2026