arXiv AI July 23, 2026 By Tao An

Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory

arXiv:2601. 00821v4 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts (extracted facts, decisions, or events) on the premise that distilled structure retrieves better than raw text.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 15

Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations

arXiv:2601. 00821v3 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts -- extracted facts, decisions, or events -- on the premise that distilled structure retrieves better than raw text.

By Tao An

llms rag efficiency benchmarks

arXiv AI

Aug 5

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.

By Yuxin Liao, Le Wu, Min Hou, Hao Liu, Han Wu, Zishu Wang

llms agents nlp

arXiv AI

Aug 11

SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents

arXiv:2608. 08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said.

By Fengrong Wan, Chengcan Wu, Ningtao Lyu

llms rag agents

arXiv AI

Jun 10

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

arXiv:2606. 09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate.

By Liuyin Wang

llms agents benchmarks

arXiv AI

Jun 6

TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management

arXiv:2606. 06337v1 Announce Type: new Abstract: Large language model (LLM) deployments for long-horizon tasks face a fundamental constraint: context windows are finite while productive work sessions are not.

By Shweta Mishra

llms benchmarks

arXiv AI

Jun 24

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.

By Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt

llms benchmarks

Related stories

Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression