SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.01280 · 2026

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

Yuxiang Wei, Huacan Wang, Ronghao Chen, Lei Zou, Sen Hu, Zhiyuan Yao, Xueran Han, Jiaxin Ran

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2601.01280.json · badge: /api/ran/2601.01280.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AvatarMemory/UnifiedMem canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
deduplicate_with_tracking Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/data_preprocessing/lme_deduplicate.py
pointer only (licence: NONE) · get_code("26a8cb5307b0a68e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_user_name Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/evals/halu_graph_eval.py
pointer only (licence: NONE) · get_code("db7adcd73b73aca7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_user_name Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/evals/halu_graph_eval.py
pointer only (licence: NONE) · get_code("6ecbf0b2441006af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_anscheck_prompt Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/evals/lme_compute_qa.py
pointer only (licence: NONE) · get_code("8e4f7c8ecedd17fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_rankings_from_retrieval_results Ran
ran, honoured the contract we drafted
AvatarMemory/UnifiedMem/evals/lme_compute_recall.py
pointer only (licence: NONE) · get_code("5b6dce41a0d60b6a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_stage_base_url Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/src/config.py
pointer only (licence: NONE) · get_code("c3e1613e2b87ef3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_stage_model Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/src/config.py
pointer only (licence: NONE) · get_code("8a66c65d3e29703b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getenv Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/src/config.py
pointer only (licence: NONE) · get_code("e726e129f7c867f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_json Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/evals/halu_graph_eval.py
pointer only (licence: NONE) · get_code("02472179dd90321e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reconstruct_deduplication_mapping Ran
ran; our contract draft was wrong, not the code
AvatarMemory/UnifiedMem/data_preprocessing/lme_deduplicate.py
pointer only (licence: NONE) · get_code("02857f981ca547ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

aggregate_eval_results Not yet run
unverified (harvested, no recorded run)
AvatarMemory/UnifiedMem/evals/halu_eval.py
pointer only (licence: NONE) · get_code("e0aab4b195550d47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

dcg Not yet run
unverified (harvested, no recorded run)
AvatarMemory/UnifiedMem/evals/lme_eval_utils.py
pointer only (licence: NONE) · get_code("c8f76a04b5265a70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

evaluate_retrieval Not yet run
unverified (harvested, no recorded run)
AvatarMemory/UnifiedMem/evals/lme_eval_utils.py
pointer only (licence: NONE) · get_code("4c538cdb253e39f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ndcg Not yet run
unverified (harvested, no recorded run)
AvatarMemory/UnifiedMem/evals/lme_eval_utils.py
pointer only (licence: NONE) · get_code("878c3d776ad1928f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

recompute_metrics_for_entry Not yet run
unverified (harvested, no recorded run)
AvatarMemory/UnifiedMem/evals/lme_compute_recall.py
pointer only (licence: NONE) · get_code("e200d9e27b970ba1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AvatarMemory/UnifiedMem when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_anscheck_prompt 3 other papers
3 dated earlier
2410.10813 (2024-10)
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
2506.09944 (2025-06)
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
2510.18866 (2025-10)
LightMem: Lightweight and Efficient Memory-Augmented Generation
dcg 2 other papers
1 dated earlier, 1 the same month
2410.10813 (2024-10)
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
2601.06966 (2026-01)
RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
evaluate_retrieval 1 other paper
1 dated earlier
2410.10813 (2024-10)
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
ndcg 1 other paper
1 dated earlier
2410.10813 (2024-10)
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Graph structures are increasingly adopted in dialog memory systems, motivated by their success in retrieval-augmented generation and the associative nature of human memory. However, empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. In this work, we present an experimental and system-oriented analysis of long-term dialog memory architectures. We formalize a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization and maintenance, as well as indexing and retrieval. Our results show that underlying implementation details-often insufficiently specified in prior work-have a substantial impact on performance, and we identify stable, reliable strong baselines to support fair comparison and practical deployment. Code are available at https: //github.com/AvatarMemory/UnifiedMem

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.01280")
get_code_for_paper("2601.01280")
have("2601.01280")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2601.01280.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2601.01280.svg)](https://syntology.ai/paper/2601.01280)

Connect an agent — have() is free.