{"arxiv_id":"2605.30723","incoming":{"papers":3,"sentences":8,"groups":[{"kind":"comparison","label":"Compares with it","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2608.09248","title":"Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution","url":"/paper/2608.09248","section":"Setup","sentence":"We compare against Zero-Shot, ReAct [ref] , Reflexion [ref] , ExpeL [ref] , and MASA [ref] ; all methods are reproduced on both Qwen3-8B and Qwen3-14B [ref] .All experiments are conducted on 8$×$H800 GPUs.Detailed dataset statistics, baseline reproduction protocols, and hyperparameter configurations are provided in the Technical Supplement.","intent_p":0.95,"contests_p":null}]},{"kind":"background","label":"Cites it as background","papers":1,"sentences":4,"quotes":[{"arxiv_id":"2608.09248","title":"Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution","url":"/paper/2608.09248","section":"Introduction","sentence":"Text-embedding retrieval [ref] matches task descriptions against skill descriptions in a shared semantic space, verbal self-reflection [ref] produces textual critiques of prior actions to inform subsequent choices, experience-based learning [ref] distills trajectory-level lessons into natural-language rules, and model-aware alignment [ref] refines skill content through text-space search.","intent_p":0.84,"contests_p":null}]}],"unlabelled_sentences":3},"outgoing":{"papers":15,"sentences":22,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":1,"sentences":2,"quotes":[{"arxiv_id":"2602.08234","title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning","url":"/paper/2602.08234","section":"Setup","sentence":"Following prior work, we adopt the skill library of [ref] as the variant and construct the and variants through controlled rewriting that preserves the underlying principles while adjusting granularity (see Table [ref] in Appendix [ref] for side-by-side examples).","intent_p":0.85,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":4,"sentences":4,"quotes":[{"arxiv_id":"2511.07568","title":null,"url":"/paper/2511.07568","section":"Introduction","sentence":"LLM agents increasingly solve long-horizon interactive tasks, including web navigation [ref] , embodied control [ref] , and tool use [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2602.20867","title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","url":"/paper/2602.20867","section":"Introduction","sentence":"LLM agents increasingly solve long-horizon interactive tasks, including web navigation [ref] , embodied control [ref] , and tool use [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2604.02268","title":"SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization","url":"/paper/2604.02268","section":"Introduction","sentence":"LLM agents increasingly solve long-horizon interactive tasks, including web navigation [ref] , embodied control [ref] , and tool use [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2605.06614","title":"SkillOS: Learning Skill Curation for Self-Evolving Agents","url":"/paper/2605.06614","section":"Introduction","sentence":"LLM agents increasingly solve long-horizon interactive tasks, including web navigation [ref] , embodied control [ref] , and tool use [ref] .","intent_p":0.97,"contests_p":null}]}],"unlabelled_sentences":16},"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/2605.30723"}}