pith. sign in

Retain the remainder (those that fail at least once); these are the tasks where a skill library could plausibly help

Discard tasks the baseline solves on all 5 seeds (∼273 tasks), since a skill library cannot possibly improve on an already-saturated task

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.AI 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

cs.AI · 2026-05-21 · conditional · novelty 6.0

Ratchet provides a minimal hygiene recipe for self-managing skill libraries in frozen LLM agents, delivering +0.328 rolling-mean pass@1 gain on MBPP+ hard-100 and +0.22 peak lift on SWE-bench Verified.

citing papers explorer

Showing 1 of 1 citing paper.

  • Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents cs.AI · 2026-05-21 · conditional · none · ref 32

    Ratchet provides a minimal hygiene recipe for self-managing skill libraries in frozen LLM agents, delivering +0.328 rolling-mean pass@1 gain on MBPP+ hard-100 and +0.22 peak lift on SWE-bench Verified.