{"arxiv_id":"2506.23149","incoming":{"papers":1,"sentences":1,"groups":[{"kind":"background","label":"Cites it as background","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":"Related Work","sentence":"Skill-based LLM agents maintain reusable procedural knowledge for long-horizon tasks [ref] , with recent work advancing skill evolution [ref] , trajectory distillation [ref] , unified training [ref] , and experiential learning [ref] .","intent_p":1.0,"contests_p":null}]}],"unlabelled_sentences":0},"outgoing":{"papers":10,"sentences":17,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","url":"/paper/1908.10084","section":"Setup","sentence":"For semantic matching between knowledge tags, we use all-MiniLM-L6-v2 [ref] with the threshold defined in [ref].","intent_p":1.0,"contests_p":null}]},{"kind":"comparison","label":"Compares with","papers":3,"sentences":3,"quotes":[{"arxiv_id":"2603.25158","title":"Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills","url":"/paper/2603.25158","section":"Setup","sentence":"Baselines We compare with three current representative SOTA skill-evolution baselines: CoEvoSkills [ref] , Trace2Skill [ref] , and SkillX [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"2604.01687","title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","url":"/paper/2604.01687","section":"Setup","sentence":"Baselines We compare with three current representative SOTA skill-evolution baselines: CoEvoSkills [ref] , Trace2Skill [ref] , and SkillX [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"2604.04804","title":"SkillX: Automatically Constructing Skill Knowledge Bases for Agents","url":"/paper/2604.04804","section":"Setup","sentence":"Baselines We compare with three current representative SOTA skill-evolution baselines: CoEvoSkills [ref] , Trace2Skill [ref] , and SkillX [ref] .","intent_p":1.0,"contests_p":null}]},{"kind":"supports_this_paper","label":"Cites as support","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2604.04323","title":"How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings","url":"/paper/2604.04323","section":"Introduction","sentence":"Consequently, the evolved skill can be incomplete or noisy, limiting its usefulness for the target task [ref] .","intent_p":0.96,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":5,"sentences":9,"quotes":[{"arxiv_id":"2601.21123","title":null,"url":"/paper/2601.21123","section":"Introduction","sentence":"Existing methods can be broadly grouped into two categories: skill-driven methods, which organize and expand existing skills [ref] , and trajectory-driven methods, which distill execution traces and failures into reusable skills [ref] .","intent_p":0.94,"contests_p":null},{"arxiv_id":"2603.01145","title":null,"url":"/paper/2603.01145","section":"Introduction","sentence":"Existing methods can be broadly grouped into two categories: skill-driven methods, which organize and expand existing skills [ref] , and trajectory-driven methods, which distill execution traces and failures into reusable skills [ref] .","intent_p":0.94,"contests_p":null},{"arxiv_id":"2603.25158","title":"Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills","url":"/paper/2603.25158","section":"Introduction","sentence":"Existing methods can be broadly grouped into two categories: skill-driven methods, which organize and expand existing skills [ref] , and trajectory-driven methods, which distill execution traces and failures into reusable skills [ref] .","intent_p":0.94,"contests_p":null},{"arxiv_id":"2604.04804","title":"SkillX: Automatically Constructing Skill Knowledge Bases for Agents","url":"/paper/2604.04804","section":"Related Work","sentence":"Recent systems such as AutoSkill [ref] and SkillX [ref] further maintain explicit skill repositories through continual extraction, refinement, hierarchical organization, and expansion from agent experiences.","intent_p":0.87,"contests_p":null},{"arxiv_id":"2602.12430","title":"Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward","url":"/paper/2602.12430","section":"Related Work","sentence":"Skill evolution aims to continually improve external skill libraries by revising, composing, specializing, and extending reusable procedural knowledge [ref] .","intent_p":0.96,"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/2506.23149"}}