SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.10715 · 2026

Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents

Jun Liu, Hui Liu, Yifei Li, Weidong Guo, Yu Xu, Lingling Zhang, Muye Huang, Rongman Xu, Lijiao Xu

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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 1 has 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/2602.10715.json · badge: /api/ran/2602.10715.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
xjtuleeyf/Locomo-Plus community
Papers with Code archive
11 ran · 5 no recorded run
FunctionStatusWhere it lives
_build_model_input Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("914a5c41650fad4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_compute_summary Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("b7f5153386e0f19b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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_openai_client Ran
ran on a synthesized input
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("30143e37aea019f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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_task_instruction Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("dceda189c5455bb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_parse_judge_response Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("4ed4c87680ca0fb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_prepend_conv_prefix Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("34802bcaf77d0e07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

call_llm Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("5c5765a0c9007c76")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

call_model Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("7e92aca251456902")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

call_test Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("ca34b992ed5a0906")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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_judge_prompt Ran
ran; our contract draft was wrong, not the code
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("457fbd7ac27fc0d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

label_to_score Ran
ran, honoured the contract we drafted
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("06a8fea429acf534")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_judge_one_record Not yet run
unverified (harvested, no recorded run)
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("92054394282a016d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_load_env_local_sh Not yet run
unverified (harvested, no recorded run)
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("285d282349ed0fc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

_print_summary Not yet run
unverified (harvested, no recorded run)
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("c6a4099105374ceb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

call_vllm Not yet run
unverified (harvested, no recorded run)
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("5d858d0bbfee493c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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.

run_judge Not yet run
unverified (harvested, no recorded run)
xjtuleeyf/Locomo-Plus/evaluation_framework/task_eval/llm_as_judge.py
pointer only (licence: NONE) · get_code("1b8262b1426a8d81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xjtuleeyf/Locomo-Plus 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 16 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.

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

Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often depend on implicit constraints such as user state, goals, or values that are not explicitly queried later. To evaluate this setting, we introduce LoCoMo-Plus, a benchmark for assessing cognitive memory under cue-trigger semantic disconnect, where models must retain and apply latent constraints across long conversational contexts. We further show that conventional string-matching metrics and explicit task-type prompting are misaligned with such scenarios, and propose a unified evaluation framework based on constraint consistency. Experiments across diverse backbone models, retrieval-based methods, and memory systems demonstrate that cognitive memory remains challenging and reveals failures not captured by existing benchmarks. Our code and evaluation framework are publicly available at: https: //github.com/xjtuleeyf/Locomo-Plus.

For agents

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

get_harvested_code_for_paper("2602.10715")
get_code_for_paper("2602.10715")
have("2602.10715")

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

curl https://syntology.ai/api/ran/2602.10715.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.10715.svg)](https://syntology.ai/paper/2602.10715)

Connect an agent — have() is free.