@omarsar0: Agents can self-improve without retraining. EvoSkill v2 achieves this with persistent agent skills. A coach agent reads…

X AI KOLs Timeline Tools

Summary

EvoSkill v2 enables AI agents to self-improve without retraining by using persistent skills stored in files, with a coach agent writing lessons from failed tasks, leading to significant performance gains in tasks like spreadsheet repair.

Agents can self-improve without retraining. EvoSkill v2 achieves this with persistent agent skills. A coach agent reads the failed runs and writes the skill. The worker loads it the next time a similar task shows up. No weights are touched. Every improvement comes from a simple file with lessons. Every bad lesson also gets saved. On spreadsheet repair, the coach found the grader trusted cached values and wrote a skill telling the worker to skip recalculation. Sentient's fix was to split the roles. The agent that writes skills cannot touch the test. A person reviews the results after every round. With that in place, the hardest spreadsheet tasks went from 3 passes out of 120 to 21.
Original Article
View Cached Full Text

Cached at: 09/19/26, 04:46 AM

Agents can self-improve without retraining.

EvoSkill v2 achieves this with persistent agent skills.

A coach agent reads the failed runs and writes the skill. The worker loads it the next time a similar task shows up.

No weights are touched. Every improvement comes from a simple file with lessons.

Every bad lesson also gets saved. On spreadsheet repair, the coach found the grader trusted cached values and wrote a skill telling the worker to skip recalculation.

Sentient’s fix was to split the roles. The agent that writes skills cannot touch the test. A person reviews the results after every round.

With that in place, the hardest spreadsheet tasks went from 3 passes out of 120 to 21.

Sentient (@SentientAGI): Last week, Dario Amodei published “We Must Pace the Frontier”.

His concern: the OpenAI–Hugging Face incident in which a swarm of agents tried to hack their own grader.

Rather than take his word for it, we used EvoSkill to test it by building a coach whose job was to make

Similar Articles

@AlphaSignalAI: https://x.com/AlphaSignalAI/status/2069064122218717387

X AI KOLs Timeline

This article explores how AI agents can automatically write and optimize their skill files using techniques like SkillOpt from Microsoft Research, which treats skill documents as trainable state and delivers significant performance improvements. It addresses the challenge of manual skill tuning and presents frameworks like GEPA and EvoSkill as evolutionary approaches.