{"arxiv_id":"2608.20274","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":16,"sentences":21,"groups":[{"kind":"supports_this_paper","label":"Cites as support","papers":2,"sentences":3,"quotes":[{"arxiv_id":"2510.15863","title":null,"url":"/paper/2510.15863","section":"Introduction","sentence":"First, a skill induced from a whole trajectory is tied to its source task ( [ref]) and generalizes poorly to new tasks [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2604.20087","title":"SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks","url":"/paper/2604.20087","section":"Related Work","sentence":"(ii) End-to-end scores hide each skill's contribution to success despite using statistics including reuse counts or library growth [ref] .","intent_p":0.96,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":7,"sentences":7,"quotes":[{"arxiv_id":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","url":"/paper/2305.17144","section":"Related Work","sentence":"Skills in agents A line of work consolidates an agent's experience into an explicit skill memory [ref] , differing along three axes ( [ref]): (i) the skill induction level, including a trajectory [ref] , a step [ref] , a rule [ref] , or a subtask [ref] ; (ii) the skill format, including text [ref] or code [ref] ; and (iii) the induction prompt, with various instructions, demonstrations, and abstraction rules [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2512.13564","title":"Memory in the Age of AI Agents","url":"/paper/2512.13564","section":"Related Work","sentence":"Skills in agents A line of work consolidates an agent's experience into an explicit skill memory [ref] , differing along three axes ( [ref]): (i) the skill induction level, including a trajectory [ref] , a step [ref] , a rule [ref] , or a subtask [ref] ; (ii) the skill format, including text [ref] or code [ref] ; and (iii) the induction prompt, with various instructions, demonstrations, and abstraction rules [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2512.17102","title":"Reinforcement Learning for Self-Improving Agent with Skill Library","url":"/paper/2512.17102","section":"Related Work","sentence":"Skills in agents A line of work consolidates an agent's experience into an explicit skill memory [ref] , differing along three axes ( [ref]): (i) the skill induction level, including a trajectory [ref] , a step [ref] , a rule [ref] , or a subtask [ref] ; (ii) the skill format, including text [ref] or code [ref] ; and (iii) the induction prompt, with various instructions, demonstrations, and abstraction rules [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2602.21611","title":null,"url":"/paper/2602.21611","section":"Related Work","sentence":"Skills in agents A line of work consolidates an agent's experience into an explicit skill memory [ref] , differing along three axes ( [ref]): (i) the skill induction level, including a trajectory [ref] , a step [ref] , a rule [ref] , or a subtask [ref] ; (ii) the skill format, including text [ref] or code [ref] ; and (iii) the induction prompt, with various instructions, demonstrations, and abstraction rules [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","url":"/paper/2601.03192","section":"Related Work","sentence":"Others train memory operations or skill-augmented policies with RL [ref] or retrieve episodes without induction [ref] .","intent_p":0.98,"contests_p":null}]}],"unlabelled_sentences":11},"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/2608.20274"}}