LongMemEval
PulseAugur coverage of LongMemEval — every cluster mentioning LongMemEval across labs, papers, and developer communities, ranked by signal.
- instance of Long Context Modeling 90%
- instance of Mem0 Agent Memory Framework 90%
- instance of locomotive class 90%
- instance of Gotit.pub 90%
- used by Long Context Modeling 70%
- instance of alphaXiv 70%
- used by DagsHub 70%
- instance of CatalyzeX 70%
- instance of ScienceCast 70%
- instance of DagsHub 70%
- competes with Mem0 Agent Memory Framework 60%
- other alphaXiv 50%
11 day(s) with sentiment data
-
New Axis-LoRA adapter enhances LLM personal memory retrieval
Researchers have developed Axis-LoRA, a novel adapter designed to improve the retrieval of personal memories from large language models. Current methods using frozen embedding models struggle to differentiate memories b…
-
RAG systems need better retrieval, not just longer context, guide says
A 2026 guide to Retrieval-Augmented Generation (RAG) systems highlights that failures often stem from the retrieval process rather than the language model itself. Despite advancements in long-context windows, retrieval …
-
RAG outperforms specialized memory systems in agent benchmarks
A recent paper highlights that Retrieval-Augmented Generation (RAG) often outperforms specialized memory systems in agent comparisons. The research indicates that many dedicated memory systems score lower than simple RA…
-
New LLM agent memory systems leverage recommendation and adaptive budgeting
Researchers have developed new methods for enhancing the long-term memory capabilities of large language model (LLM) agents. One approach, AgentMemRec, frames agent memory as a budgeted slate recommendation problem, ada…
-
AI assistants struggle with memory recall as scale increases · 2 sources tracked
A new paper explores the challenges of proactive memory recall in long-lived AI assistants. The research demonstrates that as the size of the memory store ($N$) increases, the difficulty of deciding when to interrupt th…
-
Vektor 2.0.2 boosts LongMemEval benchmark scores with enhanced memory recall
Vektor has released version 2.0.2 of its memory benchmark tool, LongMemEval, demonstrating significant improvements in its ability to recall and process information from long chat histories. The updated build achieved a…
-
Uni-Mem system learns agentic memory construction and retrieval via novel RL methods
Researchers have developed Uni-Mem, a novel system for agentic memory management that learns both memory construction and retrieval through end-to-end online reinforcement learning. To address challenges with existing R…
-
Naive RAG outperforms complex agentic memory systems, study finds
A new paper from Hugging Face suggests that simpler Retrieval-Augmented Generation (RAG) methods, which use raw conversation history, can outperform more complex agentic memory systems. The research found that Raw-RAG a…
-
New "Memory as Code" framework boosts LLM long-term memory
Researchers have introduced "Memory as Code" (MaC), a novel framework designed to enhance the long-term memory capabilities of Large Language Model (LLM) agents. MaC unifies memory construction and retrieval using a sha…
-
Keyword search rivals dedicated memory layers in LLM tests
A recent test comparing three methods for providing LLMs with memory over a dataset of 200 questions found that traditional keyword search using SQLite FTS5 performed nearly as well as a purpose-built memory layer calle…
-
AI agent memory recall vs. answer accuracy: Graph-MIND study reveals key differences
A new evaluation of AI agent memory systems highlights a significant discrepancy between retrieval recall and actual answer accuracy. While systems like agentmemory report high retrieval scores (e.g., 95% recall@5), the…
-
Tencent's Hy Memory 2.0 performance hinges on LLM quality, benchmark shows
Tencent has released Hy Memory 2.0, an open framework for managing AI memory, alongside its MemHub application. A comparative analysis using the LongMemEval benchmark revealed that Hy Memory 2.0's performance is heavily…
-
New harness evaluates AI agent memory layers beyond vendor claims
A developer has created an open-source evaluation harness to assess the effectiveness of memory layers in AI agents. The harness, named memstrata-lme500-harness, aims to provide a verifiable method for testing memory pe…
-
New T2Mem Framework Builds LLM Memory During Inference
Researchers have introduced T$^2$Mem, a novel framework for constructing memory in Large Language Models (LLMs) that defers the process to inference time. Unlike traditional methods that build memory offline, T$^2$Mem p…
-
NativeScope retrieval method leverages data structure for improved recall
Researchers have introduced NativeScope, a novel retrieval method designed to leverage the inherent structure within data, such as sections and order, rather than relying solely on semantic similarity. This approach is …
-
AI memory challenge: Noticing changes, not just recalling past chats · 1 source tracked
A recent investigation into AI memory systems suggests that the primary challenge for AI assistants is not recalling past conversations, but rather noticing when information has changed. Testing revealed that most of th…
-
New model enhances LLMs with temporal validity and explicit concept provenance
Researchers have introduced the Concept Lifecycle Model (CLM) and Concept-Grounded Attention (CGA) to enhance knowledge-intensive language models. CLM represents concepts as persistent, temporally versioned entities wit…
-
MemFold optimizes AI memory for personalization using on-policy optimization
Researchers have developed MemFold, a novel method for optimizing compact soft memory in AI assistants designed for long-context personalization. Unlike traditional approaches that compress memory into latent vectors or…
-
AI research tackles long-term memory with faster retrieval and smarter storage
Multiple research papers explore advanced memory systems for AI agents, aiming to overcome the limitations of fixed context windows and improve long-term knowledge retention. One approach, galahad-kv, uses local NVMe di…
-
New LLM memory systems tackle long-term conversation challenges · 5 sources tracked
Researchers are developing novel methods to manage and retrieve information from long-term conversational memory in Large Language Models (LLMs). These approaches aim to overcome the limitations of full-context injectio…