Agent Memory
Overview
Agent memory studies how AI systems preserve and use information beyond the current context, from personal facts and changing state to task procedures and spatial experience. Common approaches include retrieval over raw histories, summaries and vector or knowledge graphs, alongside methods that organize episodic, semantic, and procedural memory or learn when to update, compress, and forget. Evaluation spans conversational benchmarks such as LoCoMo and LongMemEval as well as multi-session web, coding, and embodied tasks, with growing attention to interference, stale information, provenance, privacy, and whether retrieved evidence actually improves later actions. A central tension is balancing reliable, generalizable memory with limited context, latency, and maintenance cost; strong recall on question-answering tests does not yet guarantee robust use in evolving environments.
Latest papers
208 papers26 papers in the last four weeks, down 32% on the four weeks before. 0.2% of all new papers.
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
M: Every Task Deserves Its Own Memory Harness
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
trust-building investment'' for one strategic goal and a contractual liability'' for another. Current memory architectures assume a single correct encoding, or at best support multiple views over unified storage. We propose Rashomon Memory: an architecture where parallel goal-conditioned agents encode experiences according to their priorities and negotiate at query time through argumentation. Each perspective maintains its own ontology and knowledge graph. At retrieval, perspectives propose interpretations, critique each other's proposals using asymmetric domain knowledge, and Dung's argumentation semantics determines which proposals survive. The resulting attack graph is itself an explanation: it records which interpretation was selected, which alternatives were considered, and on what grounds they were rejected. We present a proof-of-concept showing that retrieval modes (selection, composition, conflict surfacing) emerge from attack graph topology, and that the conflict surfacing mode, where the system reports genuine disagreement rather than forcing resolution, lets decision-makers see the underlying interpretive conflict directly.