{"arxiv_id":"2608.15165","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":7,"sentences":20,"groups":[{"kind":"data_used","label":"Uses data or values from","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2601.13183","title":null,"url":"/paper/2601.13183","section":"Experimental Setup","sentence":"To evaluate generalization in the legal domain, we select Exemption Classification (EC) and Exemption Valuation (EV) from the Advanced Competency suite of OpenExempt [ref] , with 210 induction cases and 105 held-out test cases for each task.","intent_p":0.94,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":6,"sentences":9,"quotes":[{"arxiv_id":"2603.25158","title":"Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills","url":"/paper/2603.25158","section":"Related Work","sentence":"More recent systems move beyond retaining individual memories by continually refining an evolving playbook in ACE [ref] or hierarchically consolidating trajectory-local lessons in Trace2Skill [ref] .","intent_p":0.95,"contests_p":null},{"arxiv_id":"2606.13317","title":"SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents","url":"/paper/2606.13317","section":"Related Work","sentence":"SkillGen [ref] evaluates the net intervention effect of a synthesized skill, while SkillCAT [ref] replays candidate patches on their source tasks before hierarchical merging.","intent_p":0.95,"contests_p":null},{"arxiv_id":"2605.10999","title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","url":"/paper/2605.10999","section":"Related Work","sentence":"SkillGen [ref] evaluates the net intervention effect of a synthesized skill, while SkillCAT [ref] replays candidate patches on their source tasks before hierarchical merging.","intent_p":0.95,"contests_p":null},{"arxiv_id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","url":"/paper/2602.12670","section":"Related Work","sentence":"Agent skills have emerged as reusable procedural artifacts that extend LLM agents with task instructions, operational knowledge, and executable workflows beyond one-off prompting and atomic tool use [ref] .","intent_p":0.98,"contests_p":null},{"arxiv_id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","url":"/paper/2305.16291","section":"Related Work","sentence":"Agent skills have emerged as reusable procedural artifacts that extend LLM agents with task instructions, operational knowledge, and executable workflows beyond one-off prompting and atomic tool use [ref] .","intent_p":0.98,"contests_p":null}]}],"unlabelled_sentences":10},"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/2608.15165"}}