Paper · Tools and harness
Cortex
Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and RulesA tool that tests and prunes a coding agent's harness by keeping only the skills and rules that demonstrably improve its success rate on replayable tasks.
The loop
Cortex tests changes to a coding agent's harness by saving fixes as replayable tasks and evaluating new skills or rules. It retains only those modifications that show a net gain in task success, directly evolving the agent's operating rules.
The loop
Cortex- Cortex tests harness changes
- evaluates new skills and rules
- retains only net-gain modifications
- updates the agent's harness
- Cortex tests harness changes
- evaluates new skills and rules
- retains only net-gain modifications
- updates the agent's harness
↻ The improved system does the next round, and the loop turns again.
Why it is a road to recursion
By measurement-gating harness evolution, Cortex ensures that an agent's operating rules continuously improve without regressing on previously solved tasks.
Evidence
Retains only skills or rules that show a net gain and no noticeable regression across repeated runs.
coding-agentsharness-evolutionpruning
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
Training the Whole Agent, Not Just the Model
- Teacher models evolve tools and skills
- Policy trains with adapted harness
- Policy generates new trajectories
- Trajectories guide further harness adaptation
- repeat
Tools and harnessLingxiao Tang et al. · 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