{"arxiv_id":"2608.18719","incoming":{"papers":1,"sentences":1,"groups":[{"kind":"background","label":"Cites it as background","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2608.19269","title":"What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals","url":"/paper/2608.19269","section":"Related work","sentence":"Measurement research separates constructs from operationalizations [ref] ; judge diagnostics study evaluator competence and spurious gains [ref] .","intent_p":0.87,"contests_p":null}]}],"unlabelled_sentences":0},"outgoing":{"papers":12,"sentences":15,"groups":[{"kind":"background","label":"Cites as background","papers":10,"sentences":12,"quotes":[{"arxiv_id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","url":"/paper/2507.19457","section":"Related Work","sentence":"A rapidly growing line of work equips frozen agents with reusable, natural-language skills [ref] and optimizes them automatically: offline distillation from execution traces [ref] , and online evolution through failure-driven reflection [ref] , validation-gated updates [ref] , adversarial co-evolution against a verifier [ref] , shared asset layers [ref] , credit signals [ref] , reinforcement learning over skill libraries [ref] , and skill–tool co-evolution [ref] ; reflective textual evolution can even outperform scalar-reward RL in sample efficiency [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2602.08234","title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning","url":"/paper/2602.08234","section":"Related Work","sentence":"A rapidly growing line of work equips frozen agents with reusable, natural-language skills [ref] and optimizes them automatically: offline distillation from execution traces [ref] , and online evolution through failure-driven reflection [ref] , validation-gated updates [ref] , adversarial co-evolution against a verifier [ref] , shared asset layers [ref] , credit signals [ref] , reinforcement learning over skill libraries [ref] , and skill–tool co-evolution [ref] ; reflective textual evolution can even outperform scalar-reward RL in sample efficiency [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2603.02766","title":"EvoSkill: Automated Skill Discovery for Multi-Agent Systems","url":"/paper/2603.02766","section":"Related Work","sentence":"A rapidly growing line of work equips frozen agents with reusable, natural-language skills [ref] and optimizes them automatically: offline distillation from execution traces [ref] , and online evolution through failure-driven reflection [ref] , validation-gated updates [ref] , adversarial co-evolution against a verifier [ref] , shared asset layers [ref] , credit signals [ref] , reinforcement learning over skill libraries [ref] , and skill–tool co-evolution [ref] ; reflective textual evolution can even outperform scalar-reward RL in sample efficiency [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2603.25158","title":"Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills","url":"/paper/2603.25158","section":"Related Work","sentence":"A rapidly growing line of work equips frozen agents with reusable, natural-language skills [ref] and optimizes them automatically: offline distillation from execution traces [ref] , and online evolution through failure-driven reflection [ref] , validation-gated updates [ref] , adversarial co-evolution against a verifier [ref] , shared asset layers [ref] , credit signals [ref] , reinforcement learning over skill libraries [ref] , and skill–tool co-evolution [ref] ; reflective textual evolution can even outperform scalar-reward RL in sample efficiency [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2603.28716","title":"Dynamic Dual-Granularity Skill Bank for Agentic RL","url":"/paper/2603.28716","section":"Related Work","sentence":"A rapidly growing line of work equips frozen agents with reusable, natural-language skills [ref] and optimizes them automatically: offline distillation from execution traces [ref] , and online evolution through failure-driven reflection [ref] , validation-gated updates [ref] , adversarial co-evolution against a verifier [ref] , shared asset layers [ref] , credit signals [ref] , reinforcement learning over skill libraries [ref] , and skill–tool co-evolution [ref] ; reflective textual evolution can even outperform scalar-reward RL in sample efficiency [ref] .","intent_p":0.99,"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/2608.18719"}}