Harness adapters: RL-trained LoRAs inside each agent harness beat the base model
yb2698 · x · 2026-11-07
Hesamation argues 2027 will be the year of extreme model-harness co-design, with models tuned for specific harnesses and vice versa. Lysandre Jik shares the best finding so far: "harness adapters" — small LoRAs trained with RL inside the actual agent harness they'll be used with. Same base model, different adapters for pi, opencode, hermes, etc., since the same model behaves very differently depending on tools, prompts and control flow. Early results: fewer tool calls than the base model while keeping or improving accuracy on held-out tasks.
More from coding & agent
- Agent Identity 101: one sequence diagram explains delegated, agent, and MCP auth patterns — adnan_hashmi · 2026-11-17
- How Comet improved a financial incident remediation agent's score from 0.34 to 0.57 with Opik — dl_weekly · 2026-11-17
- Jason Weston: Harness Optimization Hits 56.0, Distillation Adds 5.5 More — jaseweston · 2026-11-17
- Meta's Self-Improving Memory: agents discover their own memory skills and distill them into weights — jaseweston · 2026-11-17
- Every shows Claude Fable 5.2 building interactive games — slow but token-hungry — every · 2026-11-17
- Two free Wan2.1 ComfyUI workflow sets: native nodes vs Kijai wrapper with speed boosts — asdfghmfker · 2026-11-17