{"arxiv_id":"2608.31100","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":25,"sentences":31,"groups":[{"kind":"background","label":"Cites as background","papers":19,"sentences":19,"quotes":[{"arxiv_id":"2608.09044","title":"Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents","url":"/paper/2608.09044","section":"Experience-Based Agent Improvement","sentence":"Recent memory-based approaches similarly compress trajectories into rules, failure patterns, or reusable strategies that can be retrieved in later episodes: ReasoningBank [ref] distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences, Tree-of-Experience [ref] organizes accumulated experience into a hierarchy that supports feedback attribution and cross-task transfer, and MetaSkill-Evolve [ref] extends skill-file rewriting to the improvement procedure itself through two-timescale meta-skill evolution.","intent_p":0.81,"contests_p":null},{"arxiv_id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","url":"/paper/2509.25140","section":"Experience-Based Agent Improvement","sentence":"Recent memory-based approaches similarly compress trajectories into rules, failure patterns, or reusable strategies that can be retrieved in later episodes: ReasoningBank [ref] distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences, Tree-of-Experience [ref] organizes accumulated experience into a hierarchy that supports feedback attribution and cross-task transfer, and MetaSkill-Evolve [ref] extends skill-file rewriting to the improvement procedure itself through two-timescale meta-skill evolution.","intent_p":0.81,"contests_p":null},{"arxiv_id":"2607.05297","title":"MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution","url":"/paper/2607.05297","section":"Experience-Based Agent Improvement","sentence":"Recent memory-based approaches similarly compress trajectories into rules, failure patterns, or reusable strategies that can be retrieved in later episodes: ReasoningBank [ref] distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences, Tree-of-Experience [ref] organizes accumulated experience into a hierarchy that supports feedback attribution and cross-task transfer, and MetaSkill-Evolve [ref] extends skill-file rewriting to the improvement procedure itself through two-timescale meta-skill evolution.","intent_p":0.81,"contests_p":null},{"arxiv_id":"2604.08988","title":"SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment","url":"/paper/2604.08988","section":"Evaluating Adaptive and Self-Improving Agents","sentence":"SEA-Eval [ref] studies long-term agent evolution through sequential task interactions, while SEAGym [ref] investigates the evolution of persistent agent harnesses, including prompts, memories, tools, and workflows.","intent_p":0.93,"contests_p":null},{"arxiv_id":"2606.17546","title":"SEAGym: An Evaluation Environment for Self-Evolving LLM Agents","url":"/paper/2606.17546","section":"Evaluating Adaptive and Self-Improving Agents","sentence":"SEA-Eval [ref] studies long-term agent evolution through sequential task interactions, while SEAGym [ref] investigates the evolution of persistent agent harnesses, including prompts, memories, tools, and workflows.","intent_p":0.93,"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/2608.31100"}}