# LoCoMo

Long-term memory systems usually store facts as entries and pick them by relevance at query time, which makes facts scattered across sessions and changing over time hard to compose. MaC puts memory construction and retrieval under one code abstraction: facts become executable functions with canonical identifiers and source references, and a query is compiled into a retrieval program that an executor runs after a single planning call. On LOCOMO and LONGMEMEVAL, MaC reaches the highest overall LLM-judge score in all four evaluation settings, improving over the strongest baseline in each by up to 15.91% and 9.06%, while substantially cutting token consumption.

Long-term memory systems usually store facts as entries and pick them by relevance at query time, which makes facts scattered across sessions and changing over time hard to compose. MaC puts memory construction and retrieval under one code abstraction: facts become executable functions with canonical identifiers and source references, and a query is compiled into a retrieval program that an executor runs after a single planning call. On LOCOMO and LONGMEMEVAL, MaC reaches the highest overall LLM-judge score in all four evaluation settings, improving over the strongest baseline in each by up to 15.91% and 9.06%, while substantially cutting token consumption.

Agent memory systems typically retrieve memories by relevance to the current query and use them as contextual evidence; TrawMem instead organizes interaction histories into local threads, then assigns task-oriented roles and jointly selects complementary memories to build a task workspace. Across LoCoMo and MemGallery with four open- and closed-source backbones, macro-F1 improves by 2.23 to 3.14 points over representative memory systems; on LoCoMo, LLM-Judge scores rise by 4.07 and 4.31 percentage points over SimpleMem on Qwen3.5-9B and DeepSeek-V4-Flash, with roughly 12.8% and 5.1% fewer context tokens.

Agent memory systems typically retrieve memories by relevance to the current query and use them as contextual evidence; TrawMem instead organizes interaction histories into local threads, then assigns task-oriented roles and jointly selects complementary memories to build a task workspace. Across LoCoMo and MemGallery with four open- and closed-source backbones, macro-F1 improves by 2.23 to 3.14 points over representative memory systems; on LoCoMo, LLM-Judge scores rise by 4.07 and 4.31 percentage points over SimpleMem on Qwen3.5-9B and DeepSeek-V4-Flash, with roughly 12.8% and 5.1% fewer context tokens.

The work introduces CogMem, a training-free cognitive memory architecture built on the PEC2F (Person-Event-Concept-Claim-Fact) graph schema: dedicated Claim nodes preserve the source and target of subjective statements, dialogue turns are incrementally converted into provenance-aware graph records and consolidated into higher-level facts, and a rule-based controller driven by LLM intent parsing composes four deterministic graph operators—anchoring, traversal, intersection, and evidence grounding—to reconstruct query-relevant context; on LoCoMo and LongMemEval it performs strongly on multi-hop, temporal, and knowledge-update tasks, with ablations and a semantic-collapse probe supporting complementary contributions from epistemic separation, consolidation, and agentic retrieval.

The work introduces CogMem, a training-free cognitive memory architecture built on the PEC2F (Person-Event-Concept-Claim-Fact) graph schema: dedicated Claim nodes preserve the source and target of subjective statements, dialogue turns are incrementally converted into provenance-aware graph records and consolidated into higher-level facts, and a rule-based controller driven by LLM intent parsing composes four deterministic graph operators—anchoring, traversal, intersection, and evidence grounding—to reconstruct query-relevant context; on LoCoMo and LongMemEval it performs strongly on multi-hop, temporal, and knowledge-update tasks, with ablations and a semantic-collapse probe supporting complementary contributions from epistemic separation, consolidation, and agentic retrieval.