Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
hub
Walking down the memory maze: Beyond context limit through interactive reading
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
Switching the credited target among Raw, Source, and Canonical changes nDCG on 83.4-94.0% of queries, flips system orderings, and reverses parser-density recommendations on LoCoMo and LongMemEval-S.
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
LSTM-MAS uses a chained multi-agent architecture modeled on LSTM input, forget, and output gates to improve long-context QA performance and reduce hallucinations compared with prior multi-agent baselines.
LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
OSU-Mem shows overlapping memory helps retrieval when evidence shares tools or entities but hurts when steps are heterogeneous, with benefits on synthetic benchmarks vanishing on mixed real ones due to query mixing.
SegTreeMem organizes agent conversation history as a temporally ordered segment tree and shows improved answer quality on long-horizon benchmarks when chronological order is preserved during insertion and retrieval.
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
CALMem delivers virtually unbounded effective context for LLM conversations via an application-layer dual memory architecture with intra-session retrieval and token-adaptive injection.
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
citing papers explorer
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
-
Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks
Switching the credited target among Raw, Source, and Canonical changes nDCG on 83.4-94.0% of queries, flips system orderings, and reverses parser-density recommendations on LoCoMo and LongMemEval-S.
-
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
-
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
-
LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
LSTM-MAS uses a chained multi-agent architecture modeled on LSTM input, forget, and output gates to improve long-context QA performance and reduce hallucinations compared with prior multi-agent baselines.
-
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
-
When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents
OSU-Mem shows overlapping memory helps retrieval when evidence shares tools or entities but hurts when steps are heterogeneous, with benefits on synthetic benchmarks vanishing on mixed real ones due to query mixing.
-
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
SegTreeMem organizes agent conversation history as a temporally ordered segment tree and shows improved answer quality on long-horizon benchmarks when chronological order is preserved during insertion and retrieval.
-
DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
-
CALMem : Application-Layer Dual Memory for Conversational AI
CALMem delivers virtually unbounded effective context for LLM conversations via an application-layer dual memory architecture with intra-session retrieval and token-adaptive injection.
-
MemOS: A Memory OS for AI System
MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.