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.
Reflexion: Language agents with verbal reinforcement learning.Advances in Neural Information Processing Systems, 36, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2representative citing papers
LLM agents avoid output stalling and reduce generation tokens by 48-72% via deferred template rendering guided by Output Generation Capacity and a Format-Cost Separation Theorem.
citing papers explorer
-
Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents
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.
-
When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis
LLM agents avoid output stalling and reduce generation tokens by 48-72% via deferred template rendering guided by Output Generation Capacity and a Format-Cost Separation Theorem.