{"arxiv_id":"2608.05628","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":19,"sentences":32,"groups":[{"kind":"comparison","label":"Compares with","papers":2,"sentences":4,"quotes":[{"arxiv_id":"2604.01687","title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","url":"/paper/2604.01687","section":"Experimental Setup","sentence":"We additionally compare with two recent self-evolution methods: CoEvoSkills [ref] (since its source code is not publicly available, we implement and evaluate its framework based on the details in the paper), which co-evolves skills with surrogate verification, and SkillRevise [ref] , which performs trace-conditioned sequential revision.","intent_p":0.88,"contests_p":null},{"arxiv_id":"2606.01139","title":"SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision","url":"/paper/2606.01139","section":"Experimental Setup","sentence":"We additionally compare with two recent self-evolution methods: CoEvoSkills [ref] (since its source code is not publicly available, we implement and evaluate its framework based on the details in the paper), which co-evolves skills with surrogate verification, and SkillRevise [ref] , which performs trace-conditioned sequential revision.","intent_p":0.88,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":11,"sentences":16,"quotes":[{"arxiv_id":"2606.01139","title":"SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision","url":"/paper/2606.01139","section":"Related Work","sentence":"Methods closer to our setting revise skills using task-specific executions: SkillEvolver refines domain skills by evaluating fresh-agent deployments across a provided training split [ref] , CoEvoSkills co-evolves skill generation with surrogate verification [ref] , and SkillRevise sequentially refines an incumbent skill from execution traces [ref] .","intent_p":0.85,"contests_p":null},{"arxiv_id":"2605.10500","title":"SkillEvolver: Skill Learning as a Meta-Skill","url":"/paper/2605.10500","section":"Related Work","sentence":"Methods closer to our setting revise skills using task-specific executions: SkillEvolver refines domain skills by evaluating fresh-agent deployments across a provided training split [ref] , CoEvoSkills co-evolves skill generation with surrogate verification [ref] , and SkillRevise sequentially refines an incumbent skill from execution traces [ref] .","intent_p":0.85,"contests_p":null},{"arxiv_id":"2604.01687","title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","url":"/paper/2604.01687","section":"Related Work","sentence":"Methods closer to our setting revise skills using task-specific executions: SkillEvolver refines domain skills by evaluating fresh-agent deployments across a provided training split [ref] , CoEvoSkills co-evolves skill generation with surrogate verification [ref] , and SkillRevise sequentially refines an incumbent skill from execution traces [ref] .","intent_p":0.85,"contests_p":null},{"arxiv_id":"2604.03964","title":"SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources","url":"/paper/2604.03964","section":"Introduction","sentence":"Existing approaches to self-evolving skills generally follow one of two paradigms: 1) text-space optimization, which treats skill instructions as an optimizable parameter space to compute textual language gradients [ref] ; or 2) experience-based approaches, which distill procedural heuristics from execution traces or cross-task trajectories [ref] .","intent_p":0.96,"contests_p":null},{"arxiv_id":"2604.08618","title":"SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support","url":"/paper/2604.08618","section":"Introduction","sentence":"Existing approaches to self-evolving skills generally follow one of two paradigms: 1) text-space optimization, which treats skill instructions as an optimizable parameter space to compute textual language gradients [ref] ; or 2) experience-based approaches, which distill procedural heuristics from execution traces or cross-task trajectories [ref] .","intent_p":0.96,"contests_p":null}]}],"unlabelled_sentences":12},"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/2608.05628"}}