SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.10481 · 2026

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples

Kexin Huang, Xiang Wang, Jingren Zhou, Xiangnan He, Junkang Wu, Jiancan Wu, Guoyin Wang, Jinda Lu, Chiyu Ma, Yang Shuo

arXiv · PDF

Code that ran

9 of 11 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; 8 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/2607.10481.json · badge: /api/ran/2607.10481.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
Hesse73/ARMOR canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_ce_dpo_loss_rm Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/recipe/prime/prime_core_algos.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("f220595adfc5e83c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_detach_dpo_loss_rm Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/recipe/prime/prime_core_algos.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("4d91e4383716e42c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_online_dpo_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hesse73/ARMOR/verl/recipe/spin/core_algos.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("f19825983a523003")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_onlinedpo_pref Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/recipe/spin/core_algos.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("41b6e81dc3ecba79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_config_from_args Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/verl/model_merger/base_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("8896f4e2bafe8abc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_dynamic_pipeline_shards Ran
ran, honoured the contract we drafted
Hesse73/ARMOR/verl/verl/model_merger/megatron_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("94209884dcb2308e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_kl_controller Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/recipe/spin/core_algos.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("757d109d90121142")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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.

reward_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Hesse73/ARMOR/verl/recipe/r1/reward_score.py
pointer only (licence: NONE) · get_code("c30b2a96103abd2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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.

unpad_dataproto Ran
ran; our contract draft was wrong, not the code
Hesse73/ARMOR/verl/verl/protocol.py
pointer only (licence: NONE) · get_code("83b1686d7ac03c21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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_weight_loader Not yet run
unverified (harvested, no recorded run)
Hesse73/ARMOR/verl/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("acf240079d434746")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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.

get_weight_saver Not yet run
unverified (harvested, no recorded run)
Hesse73/ARMOR/verl/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("cd6b1e0d6afb2762")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hesse73/ARMOR 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 4 the same month, 10 later) and 0 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
unpad_dataproto 89 other papers
79 dated earlier, 2 the same month, 5 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
get_weight_loader 58 other papers
49 dated earlier, 2 the same month, 5 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2505.14362 (2025-05)
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
2505.20046 (2025-05)
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
and 55 more not named here
generate_config_from_args 57 other papers
44 dated earlier, 4 the same month, 6 later, 3 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 54 more not named here
get_dynamic_pipeline_shards 52 other papers
39 dated earlier, 3 the same month, 8 later, 2 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 49 more not named here
compute_ce_dpo_loss_rm 46 other papers
40 dated earlier, 3 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
and 43 more not named here
compute_detach_dpo_loss_rm 44 other papers
38 dated earlier, 3 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
and 41 more not named here
compute_online_dpo_loss 38 other papers
32 dated earlier, 3 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
and 35 more not named here
get_kl_controller 38 other papers
32 dated earlier, 3 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
and 35 more not named here
compute_onlinedpo_pref 30 other papers
24 dated earlier, 3 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
and 27 more not named here
reward_func 28 other papers
25 dated earlier, 1 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
2505.14362 (2025-05)
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
and 25 more not named here
get_weight_saver 12 other papers
12 dated earlier
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2510.04678 (2025-10)
Multi-Agent Tool-Integrated Policy Optimization
2602.12036 (2026-02)
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
and 9 more not named here

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

Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this work, we investigate a critical source of this instability: over-optimization, where models exploit training heuristics at the expense of generalizable reasoning. While reverse KL regularization is the standard defense against such degradation, our analysis reveals that it is often insufficient in this regime, as it fails to ensure comprehensive coverage of the reference distribution. To address this, we propose ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization. AR-MOR comprises two key components: (1) Anchor Rollout, which leverages off-policy data from the reference policy to preserve established solution patterns; and (2) Mixed Optimization, which reformulates the policy objective to enable controlled exploration without relying on auxiliary losses. Extensive experiments on reasoning benchmarks validate that ARMOR effectively mitigates validation collapse, enabling sustained performance improvements over extended training horizons.

For agents

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

get_harvested_code_for_paper("2607.10481")
get_code_for_paper("2607.10481")
have("2607.10481")

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

curl https://syntology.ai/api/ran/2607.10481.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.10481.svg)](https://syntology.ai/paper/2607.10481)

Connect an agent — have() is free.