SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.08086 · 2026

Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

Ge Li, Xue Jiang, Yihong Dong, Yongding Tao, Huanyu Liu, Xuning He, Zinan Sheng

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 failures of our instrument; 1 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/2608.08086.json · badge: /api/ran/2608.08086.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
Hxnng/Archer community
Papers with Code archive
7 ran · 1 no recorded run
FunctionStatusWhere it lives
ArcherDiagnostics Ran
ran on a synthesized input · constructed an object; no result was computed
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("46efa52e6bb88c12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

_forward_with_kv Ran
ran; our contract draft was wrong, not the code
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("750b09aab8ef1a16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

_saber_step Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("130d0a3007837131")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

add_gumbel_noise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("10e530678395c16a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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_prefix_cache Ran
ran; our contract draft was wrong, not the code
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("43931e9166f6ea1f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

cached_forward_logits Ran
ran; our contract draft was wrong, not the code
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("6b8388a16d72a606")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

generation_hamming_distance Ran
ran; our contract draft was wrong, not the code
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("75d00e8116d83835")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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.

generate_archer Not yet run
unverified (harvested, no recorded run)
Hxnng/Archer/src/archer/state_distance/sampler.py
pointer only (licence: NONE) · get_code("07a5c3dfc501b7d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hxnng/Archer 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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
add_gumbel_noise
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2603.01331 (2026-03)
MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models

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

Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irreversible autoregressive generation, but makes inference costly. Every denoising update alters the global context, forcing both prompt and response states to be recomputed even though only response tokens are revisable. Key-value (KV) caching could reduce this cost, yet conventional caching assumes immutable historical states and is therefore difficult to reconcile with rollback; in this paper, we introduce Adaptive Reuse of Cached Hidden States for Efficient Rollback (Archer), a training-free KV caching method for rollback-capable DLMs. Archer asymmetrically keeps the mutable response synchronized with the current hypothesis while reusing prompt K/V within a bounded state neighborhood. Although prompt representations also change under bidirectional attention, their token identities remain fixed; bounded reuse therefore amortizes repeated prompt computation without caching mutable response states. It also delays feedback from tentative tokens, reducing premature reinforcement of transient high-confidence errors and giving rollback more opportunity to correct them. Our analysis characterizes prompt reuse as a reversibility-aligned cache boundary, bounds its state-dependent approximation error, and gives a decoder-margin condition for preserving fullrefresh decisions; meanwhile, existing DLM acceleration often trades quality for speed. Archer shifts this frontier, attaining the best mean performance of 33.63% together with a 2.57× mean speedup on the main suite. Across evaluated settings, it improves Pass@1 by up to 3.05 points and reaches up to 2.95× speedup. Controlled analyses connect the quality gain to delayed prompt feedback and validate state-aware refresh. Our code is available at https://github.com/Hxnng/Archer.

For agents

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

get_harvested_code_for_paper("2608.08086")
get_code_for_paper("2608.08086")
have("2608.08086")

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

curl https://syntology.ai/api/ran/2608.08086.json

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

[![Syntology run record](https://syntology.ai/api/ran/2608.08086.svg)](https://syntology.ai/paper/2608.08086)

Connect an agent — have() is free.