Paper Detail

Long-Term Agent Memory through Complementary Curation and Consolidation

Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz, Wei-Ning Chen, Mayukh Das, Victor Rühle, Saravan Rajmohan

arxiv Score 13.3

Published 2026-10-29 · First seen 2026-10-30

Research Track A · General AI

Abstract

Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{gupta2026long,
  title = {Long-Term Agent Memory through Complementary Curation and Consolidation},
  author = {Abhishek Gupta and Dongge Han and Daniel Madrigal Diaz and Wei-Ning Chen and Mayukh Das and Victor Rühle and Saravan Rajmohan},
  year = {2026},
  abstract = {Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform },
  url = {https://arxiv.org/abs/2610.39790},
  keywords = {cs.AI, cs.MA},
  eprint = {2610.39790},
  archiveprefix = {arXiv},
}

Metadata

{}