APDMem, a hierarchical long-term memory architecture for personalized LLM assistants, achieves strong performance on the LongMemEval benchmark while accessing only 8% of total conversations, according…
A rank-based memory controller called CTWM cut prompt tokens by 24.48% on LongMemEval with aggregate accuracy parity, according to an arXiv paper (2610.00010) on heavy-tailed memory traces in long-hor…
A new arXiv paper (2610.00010v1) proposes Core-Tail World Model (CTWM), a rank-based memory controller that allocates prompt budget with a single exponent τ while retaining a summarized tail, after a …
Three founders shipped production AI agents built on Claude Managed Agents in under two weeks, including a meeting-brief assistant with a second grading agent, a cross-account sales agent fleet called…
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…
A new arXiv paper (2609.16730v1) introduces LSREP, a Longitudinal State-Replay Evaluation Protocol for conversational memory, with ICE v2 as its audited local-first architecture case study. The privat…
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 …
A new arXiv study (2608.28978v1) finds that a graph-based memory framework for long-term LLM agents underperforms a flat vector baseline on the LongMemEval benchmark, with token F1 of 0.417 versus 0.4…
Decispher launched a persistent memory layer for coding agents that cuts token usage by 38×, according to its LongMemEval benchmarks, by organizing context from GitHub, documentation, and engineering …
Ali introduced Decispher, a context and memory layer for coding agents, on Hacker News, reporting that its Memory Plane achieves 89% accuracy on LongMemEval's oracle split using GPT-4.1-mini, 81% on L…
Awareness Local, a local-first MCP memory server for AI coding agents, achieves a 96% Recall@5 on the LongMemEval benchmark (ICLR 2025) with 500 human-curated questions, running fully offline on an Ap…
A new benchmark called RENDER shows that memory formats can boost large language model accuracy by up to 72.6 points, with matched-budget 'resolved packets' outperforming recency-truncated raw dialogu…
A new benchmark called RENDER, introduced in an arXiv paper (arXiv:2608.23568v1), shows that the format of reader-facing memory artifacts can swing LLM memory evaluation scores by up to 72.6 points. O…
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 …
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…
A developer discovered that the widely-cited LOCOMO benchmark for AI memory excludes 22.5% of its questions—those testing whether a system can correctly say 'I don't know'—and instructs models to neve…
Swafra, an open-source semantic memory system for AI assistants, achieved 94.7% recall_all@10 on the LongMemEval benchmark for long-term memory. The tool works as an MCP server with Claude Desktop, Cl…
Oracle Agent Memory, a database-native memory substrate built on Oracle Database, achieves 93.8% accuracy on LongMemEval while using about 10.7x fewer tokens than flat-history baselines, according to …
Researchers introduced NapMem, a framework that transforms long-term user memory into a structured action space for conversational agents, enabling active navigation across memory granularities. Train…