Pith. sign in

REVIEW 15 cited by

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.05029 v1 pith:A6GCVZGV submitted 2023-10-08 cs.CL

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

classification cs.CL
keywords contextlongtextbeyondinformationinteractivelargelong-text
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined context window is bound to be limited. Despite attempts to extend the context window through methods like extrapolating the positional embedding, using recurrence, or selectively retrieving essential parts of the long sequence, long-text understanding continues to be a challenge. We propose an alternative approach which instead treats the LLM as an interactive agent, allowing it to decide how to read the text via iterative prompting. We introduce MemWalker, a method that first processes the long context into a tree of summary nodes. Upon receiving a query, the model navigates this tree in search of relevant information, and responds once it gathers sufficient information. On long-text question answering tasks our method outperforms baseline approaches that use long context windows, recurrence, and retrieval. We show that, beyond effective reading, MemWalker enhances explainability by highlighting the reasoning steps as it interactively reads the text; pinpointing the relevant text segments related to the query.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Evaluating Very Long-Term Conversational Memory of LLM Agents

    cs.CL 2024-02 unverdicted novelty 8.0

    Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.

  2. Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki

    cs.CL 2026-05 unverdicted novelty 7.0

    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.

  3. Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks

    cs.IR 2026-05 unverdicted novelty 7.0

    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.

  4. SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

    cs.CL 2026-05 unverdicted novelty 7.0

    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.

  5. OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory

    cs.CL 2026-04 unverdicted novelty 7.0

    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.

  6. LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding

    cs.CL 2026-01 unverdicted novelty 7.0

    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.

  7. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

    cs.CL 2024-10 unverdicted novelty 7.0

    LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.

  8. Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

    cs.IR 2024-09 unverdicted novelty 7.0

    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 gap...

  9. When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents

    cs.IR 2026-06 unverdicted novelty 5.0

    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.

  10. Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents

    cs.CL 2026-06 unverdicted novelty 5.0

    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.

  11. DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  12. CALMem : Application-Layer Dual Memory for Conversational AI

    cs.IR 2026-05 unverdicted novelty 5.0

    CALMem delivers virtually unbounded effective context for LLM conversations via an application-layer dual memory architecture with intra-session retrieval and token-adaptive injection.

  13. ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education

    cs.IR 2026-02 conditional novelty 5.0

    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.

  14. MemOS: A Memory OS for AI System

    cs.CL 2025-07 unverdicted novelty 5.0

    MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.

  15. A Survey on Retrieval-Augmented Text Generation for Large Language Models

    cs.IR 2024-04 unverdicted novelty 2.0

    A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.