SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.05096 · 2026

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

Yang Li, Lang Cao, Hanbing Liu

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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; 2 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/2604.05096.json · badge: /api/ran/2604.05096.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
hbing-l/chronos canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
build_prompt Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/baselines/memit.py
pointer only (licence: NONE) · get_code("22a46266c7fa5cbf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

build_prompt_from_quad Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/baselines/wise.py
pointer only (licence: NONE) · get_code("74fc5d08176401ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

build_quad_prompt Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/baselines/rome.py
pointer only (licence: NONE) · get_code("9301c18a0a8d51b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

dedup_docs Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/baselines/react.py
pointer only (licence: NONE) · get_code("232549a169d1766f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

evaluate_qa_exact_match Ran
ran, honoured the contract we drafted
hbing-l/chronos/utils.py
pointer only (licence: NONE) · get_code("f9e57c3241f7e934")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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_llm_response Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/llm_api.py
pointer only (licence: NONE) · get_code("224e303e6f6b90bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

load_qa_jsonl Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/chronos.py
pointer only (licence: NONE) · get_code("9661f2c79b21c5f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

normalize_label Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/utils.py
pointer only (licence: NONE) · get_code("171ec02a38b9da86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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_timestamp Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/baselines/memit.py
pointer only (licence: NONE) · get_code("9681ae4f3d68b7ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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.

quad_to_text Ran
ran; our contract draft was wrong, not the code
hbing-l/chronos/utils.py
pointer only (licence: NONE) · get_code("41b965afb020e632")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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_llm_embedding Not yet run
unverified (harvested, no recorded run)
hbing-l/chronos/llm_api.py
pointer only (licence: NONE) · get_code("492716b163adda46")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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_quads Not yet run
unverified (harvested, no recorded run)
hbing-l/chronos/baselines/memit.py
pointer only (licence: NONE) · get_code("8aa0c49892326328")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hbing-l/chronos 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although existing approaches, such as continual finetuning, knowledge editing, and retrieval-augmented generation (RAG), aim to update or supplement model knowledge, they are rarely evaluated in settings that reflect chronological, evolving, and realworld knowledge evolution. In this work, we introduce a new benchmark of real-world dynamic events, constructed from time-stamped evidence that captures how knowledge evolves over time, which enables systematic evaluation of model adaptation under continuous knowledge drift. The benchmark reveals that most existing methods, including vanilla RAG and several learning-based approaches, struggle under this setting, exposing critical limitations such as catastrophic forgetting and temporal inconsistency. To mitigate these limitations, we propose a time-aware retrieval baseline, Chronos, which progressively organizes retrieved evidence into an Event Evolution Graph to enable more temporally consistent understanding in LLMs without additional training. Overall, this work provides a foundation for analyzing and advancing LLM adaptation to continuous knowledge drift in realistic settings. Code is available at https://github.com/hbing-l/chronos.

For agents

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

get_harvested_code_for_paper("2604.05096")
get_code_for_paper("2604.05096")
have("2604.05096")

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

curl https://syntology.ai/api/ran/2604.05096.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.05096.svg)](https://syntology.ai/paper/2604.05096)

Connect an agent — have() is free.