A developer building Pryzm Memory, a remote Model Context Protocol (MCP) server, demonstrated how connecting multiple AI assistants to a single shared memory endpoint lets context saved in one assista…
A raw-conversation-turn memory system using a single Postgres table and three MCP search tools scored F1 = 0.665 on the LoCoMo benchmark with Claude Sonnet (full 10 samples), beating Omni-SimpleMem's …
Researchers submitted SpeakerMem-R1, a speaker-centered dual-track memory system for multi-party dialogue, to arXiv on 22 Sep 2026. SpeakerMem-R1 achieved 62.33% on the publicly reported EverMemBench …
Researchers proposed REALM, a reconsolidation-evolution agentic long-term memory framework for LLM agents that models memory as a continual lifecycle, organizing memories into a heterogeneous cognitiv…
Tencent researchers introduced T-Mem, a long-term memory system for LLM agents that pre-saves contextual triggers at memory write time rather than relying on semantic similarity at retrieval. The appr…
Researchers proposed CueMem, a cue-guided framework that reconstructs query-relevant dialogue context from source turns to improve long-term conversational memory for LLM agents. In experiments on the…
A new benchmark called MERIT (Memory Evaluation for Realistic Instrumented Tasks) shows that long-term memory lifts dependent-task success for tool-using LLM agents from a leak-verified floor of 0.00 …
EdgeMem, a new agent-memory method that preserves original interaction turns in a multi-anchor hypergraph built by lightweight local processing, achieved the highest strict-judge score among seven rep…
InfiniteMem, a deterministic, self-hosted episodic memory system for AI agents, reports a LoCoMo QA score of 70.49% and claims a capacity of 1 million episodes or 145 million tokens per deployment, ro…
Researchers introduced MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills, enabling skill libraries to evolve via refinement, induction, consolidation…
Researchers introduced HeadWiseKV, a training-free framework that compresses residual global KV caches in hybrid long-context language models under a budget, preserving quality while reducing memory. …
A developer warns that LLM memory systems in production fail silently because retrieval quality degrades while dashboards remain green. The analysis cites benchmarks showing leading systems score 92.5…
A new arXiv paper argues that production AI agents fail primarily due to poor context management rather than reasoning limitations, proposing a discipline called Agentic Context Management (ACM) with …
A developer benchmarked a homelab agent memory stack on the LoCoMo benchmark and improved accuracy from 63% to 80% by adding hybrid search with BM25 and a local reranker. The developer found that dens…
Recordari, a custom memory graph built by developer Corby, scored 0.831 on the LoCoMo benchmark, outperforming Microsoft Research's Memora, which published a score of 0.801. The benchmark, run with th…
The BEAM benchmark, developed by the team behind Suprflo, evaluates AI agent memory over long, multi-session histories with changing facts, ranging from 100K to 10 million tokens. It measures distinct…
Backboard, a Canadian AI infrastructure company, reported a 99.95% score on the LoCoMo memory benchmark by post-training memory directly into model weights, rather than using retrieval. The company pr…
A July 2026 paper (arXiv 2607.01935) identifies 'ghost memory' as a state coordination failure in agent memory systems, where old, current, and transition facts coexist and mislead the model, and repo…
Researchers introduced AgentMemBench, a benchmark evaluating five long-term memory strategies for conversational AI agents across three datasets and 491 annotated question turns, finding that external…
Researchers introduced CoMem (Comprehension Memory), a method that leverages the depth division of labor in large language models to enable unbounded-context memory. In evaluations, CoMem achieved 97.…