Long Context Modeling
PulseAugur coverage of Long Context Modeling — every cluster mentioning Long Context Modeling across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New benchmark and memory architecture for LLM agents unveiled
Researchers have introduced MemHop, a new benchmark designed to evaluate the multi-hop reasoning capabilities of Large Language Model (LLM) agents. This benchmark consists of 1,000 questions with evidence annotations ac…
-
Researcher fails to build LLM alternative after 8 months and 200 experiments
A researcher documented an eight-month project attempting to build a system that could accumulate experience and improve behavior without retraining large language models. The effort involved approximately 200 failed ex…
-
New framework enhances AI conversational memory with user-aware recall
Researchers have developed a new framework called Profile-guided Personalized Retrieval Optimization (PPRO) to enhance the long-term memory recall capabilities of conversational AI agents. This system creates user profi…
-
Microsoft unveils Memora memory system for AI agents
Microsoft Research has introduced Memora, a novel memory system designed to enhance the capabilities of AI agents in long-horizon tasks. Memora addresses the stateless nature of current AI models by decoupling memory co…
-
New research tackles LLM long-term memory limitations
Two new research papers, MemTrace and T-Mem, introduce novel approaches to improving long-term memory in large language model agents. MemTrace focuses on evaluating memory by knowledge points rather than individual ques…
-
Verbatim LLM conversation chunks outperform extracted facts in memory retrieval
A new research paper challenges the common practice of distilling long LLM conversations into structured artifacts like facts or events. The study found that using verbatim conversation chunks significantly outperformed…
-
LLM Memory Systems Outperform Full Context on Long Histories
A new benchmark, LongMemEval, has demonstrated that retrieval-based memory systems outperform full-context baselines for LLM agents dealing with long conversation histories. While full context remains competitive for sh…
-
ConvMemory v2 boosts conversational memory retrieval accuracy
Researchers have introduced ConvMemory v2, an advanced reranker designed to improve conversational memory retrieval. This system refines the top candidate memories identified by a previous version, ConvMemory v1, by reo…
-
New benchmarks and methods tackle LLM long-context and memory challenges
Researchers are developing new methods to improve how large language models handle long conversation histories and complex documents. Several papers introduce novel architectures and benchmarks designed to overcome the …
-
New methods enhance search result reranking with adaptive and long-context AI
Researchers have developed new methods to improve the reranking of search results, particularly in zero-resource scenarios where traditional supervised training is not feasible. One approach, DART, adapts a scoring func…
-
FluxMem framework enhances LLM agent memory with evolving graph topology
Researchers have introduced FluxMem, a novel memory framework designed to enhance the capabilities of LLM agents in dynamic environments. Unlike traditional static memory systems, FluxMem models memory as a continuously…
-
LLM memory paging uses keyword bookmarks for long conversations
A new research paper introduces cooperative memory paging, a technique designed to help Large Language Models (LLMs) manage conversations that exceed their context window. This method replaces evicted conversation segme…
-
Study shows training data curriculum fine-tunes RL agent specialization
A new study on arXiv explores how different training data curricula impact the performance of reinforcement learning (RL) agents designed to work with large language models (LLMs) and external memory banks. The research…
-
DeferMem framework enhances LLM long-term memory QA with RL
Researchers have developed DeferMem, a new framework designed to improve question answering for large language model agents dealing with long-term conversational memory. This system separates the process into initial br…
-
New frameworks enhance AI dialogue memory and retrieval benchmarks
Researchers have developed new frameworks for improving long-term dialogue agents and evaluating conversational retrieval. MGRetrieval enhances memory retrieval by grounding reflective processes in historical memory str…
-
HyMem architecture boosts LLM agent memory efficiency by 92.6%
Researchers have developed HyMem, a novel hybrid memory architecture designed to improve the efficiency and effectiveness of large language model (LLM) agents in long-context scenarios. HyMem utilizes a dual-granular st…
-
EviMem improves conversational memory retrieval with evidence gap diagnosis
Researchers have developed EviMem, a novel framework for improving long-term conversational memory by iteratively refining retrieval queries. Unlike previous methods, EviMem explicitly identifies and addresses "evidence…
-
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
Multiple research papers released on arXiv propose novel frameworks for enhancing the memory capabilities of Large Language Model (LLM) agents. These approaches aim to overcome limitations in handling long-term conversa…
-
ZenBrain AI integrates 15 neuroscience models for advanced memory architecture
Researchers have introduced ZenBrain, a novel 7-layer memory architecture for AI systems inspired by neuroscience principles. Unlike existing AI memory systems that use engineering metaphors, ZenBrain integrates concept…
-
AI memory systems mimic human forgetting with 52% retention
Researchers have developed a new AI memory system that mimics the human brain's forgetting process, achieving 52% memory persistence. This system, named YourMemory and LoCoMo, is slated for release in 2026. The developm…