{"arxiv_id":"2607.03238","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":11,"sentences":17,"groups":[{"kind":"background","label":"Cites as background","papers":9,"sentences":14,"quotes":[{"arxiv_id":"2603.22455","title":"SkillRouter: Skill Routing for LLM Agents at Scale","url":"/paper/2603.22455","section":"Introduction","sentence":"Skill retrieval and selection investigates how agents discover, route, and compose skills from large repositories [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2603.15401","title":"SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?","url":"/paper/2603.15401","section":"Introduction","sentence":"Related work also evaluates skill effectiveness on downstream tasks [ref] and identifies security risks in shared skill repositories [ref] .","intent_p":0.94,"contests_p":null},{"arxiv_id":"2605.07358","title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","url":"/paper/2605.07358","section":"Introduction","sentence":"Existing research generally treats a published skill as a reusable artifact and can be organized around four closely related aspects [ref] .","intent_p":0.92,"contests_p":null},{"arxiv_id":"2604.09297","title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","url":"/paper/2604.09297","section":"The Agent Skills Ecosystem","sentence":"Skill acquisition examines how skills are created from human expertise, agent experience, task requirements, or external resources [ref] , while skill retrieval and selection asks how an LLM agent should discover, route, and compose skills from large pools [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"2605.27366","title":"MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation","url":"/paper/2605.27366","section":"The Agent Skills Ecosystem","sentence":"Skill acquisition examines how skills are created from human expertise, agent experience, task requirements, or external resources [ref] , while skill retrieval and selection asks how an LLM agent should discover, route, and compose skills from large pools [ref] .","intent_p":1.0,"contests_p":null}]}],"unlabelled_sentences":3},"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/2607.03238"}}