← Monday, October 12, 2026AgentsPaper

Mara Chain improves AI-system optimization by refining rejected candidates

huggingface.co by Yubin Lyu et al. Editor score 8/10

Mara Chain retains and refines rejected prompts, skills, harnesses, or code instead of discarding them; across three optimization tasks it reports up to 20.5% relative improvement over named alternatives. Preserving failure information can reduce repeated mistakes in system-level agent tuning.

What

Mara Chain refines rejected candidates during optimization of prompts, skills, harnesses, and code instead of discarding them.

Method

It uses evidence from prior attempts, limits each refinement chain to a fixed depth, and applies Pareto-filtered Top-N selection to bound the candidate pool.

Why it matters

Across three optimization tasks it delivered greater performance gains with fewer rollouts; on AppWorld it reached the target score with 65.5% fewer rollouts than GEPA.

Read on huggingface.co → Code · 963 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.