KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents
- Published
- Source
- arXiv
- Paper number
- 1386
- Field
- AI Agents
- arXiv ID
- 2610.39884
Key points
- It splits knowledge into six modules of role, domain, experience, constraints, output protocol, and action descriptions, and allows at most three atomic mutations per cycle.
- A deterministic verifier maps failures to candidate modules by error class and protocol codes, and a Critic compares failed and successful trajectories together to propose edits.
- When the validation gain falls below the θ = 0.01 threshold, the full pre-edit knowledge snapshot is restored to prevent regressions.
- Across 18 domain–model settings, it raises the average hold-out score from 30.19 to 39.15, a gain of 8.96 points, or 29.7%.
- Removing either the successful or failed trajectory channel more than halves the average hold-out gain.
- Knowledge evolved on one domain transfers to other domains without further adaptation, yielding an average gain of 8.54 points across the 30 source–target pairs.
Paper links
External research summaries. These are not HDATF publications or measured product results.