{"arxiv_id":"2606.14239","incoming":{"papers":6,"sentences":7,"groups":[{"kind":"background","label":"Cites it as background","papers":4,"sentences":4,"quotes":[{"arxiv_id":"2608.12851","title":"Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents","url":"/paper/2608.12851","section":"Related Work","sentence":"Agent skills have become a persistent adaptation layer that turns interaction traces into reusable procedures through extraction, maintenance, failure analysis, verification, and utility gates [ref] .","intent_p":0.96,"contests_p":null},{"arxiv_id":"2608.09629","title":"Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?","url":"/paper/2608.09629","section":"Related Work","sentence":"SkillOS, HDSO, and SkillAudit place structure in curator learning, prospective hypothesis testing, or paired verification and rollback [ref] .","intent_p":0.88,"contests_p":null},{"arxiv_id":"2608.06880","title":"SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time","url":"/paper/2608.06880","section":"Related Work","sentence":"Execution-grounded skill refinement methods revise reusable skills using execution traces, tests, or rollout outcomes [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"2608.09555","title":"Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents","url":"/paper/2608.09555","section":"Skill-Augmented LLM Agents","sentence":"SkillEvolver [ref] , SkillAudit [ref] , and SkillHone [ref] improve skill repositories through generation, auditing, and revision.","intent_p":0.95,"contests_p":null}]}],"unlabelled_sentences":3},"outgoing":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2606.14239"}}