{"arxiv_id":"2607.13157","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":20,"sentences":37,"groups":[{"kind":"supports_this_paper","label":"Cites as support","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","url":"/paper/2404.13501","section":"Introduction","sentence":"Memory in agentic systems spans multiple forms, functions, and temporal dynamics, and is not adequately characterized by a simple short-term versus long-term dichotomy [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":"Introduction","sentence":"Memory in agentic systems spans multiple forms, functions, and temporal dynamics, and is not adequately characterized by a simple short-term versus long-term dichotomy [ref] .","intent_p":0.99,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":9,"sentences":11,"quotes":[{"arxiv_id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","url":"/paper/2507.05257","section":"Memory Benchmarks","sentence":"MemoryAgentBench moves further toward online agent behavior by testing incremental multi-turn interactions in which memory must support repeated decision making rather than a single isolated answer [ref] .","intent_p":0.84,"contests_p":null},{"arxiv_id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","url":"/paper/2402.17753","section":"Evaluation and Benchmarking","sentence":"Section 3 described related benchmarks, including LoCoMo and MemoryAgentBench [ref] .","intent_p":0.97,"contests_p":null},{"arxiv_id":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","url":"/paper/2501.13956","section":"Contemporary Agent-Memory Systems","sentence":"Zep represents agent memory through a temporal knowledge graph that supports evolving entities and relationships over time [ref] .","intent_p":0.96,"contests_p":null},{"arxiv_id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","url":"/paper/2504.19413","section":"Contemporary Agent-Memory Systems","sentence":"Mem0 extracts, consolidates, and retrieves salient conversational information, including graph-based variants for relational memory [ref] .","intent_p":0.96,"contests_p":null},{"arxiv_id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","url":"/paper/2502.12110","section":"Contemporary Agent-Memory Systems","sentence":"A-Mem proposes agentic memory organization in which new memories can trigger linking and evolution of prior records [ref] .","intent_p":0.91,"contests_p":null}]}],"unlabelled_sentences":24},"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/2607.13157"}}