SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.10048 · 2026

Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimization

Lu Yin, Xilu Wang, Xinchen Han, Hossam Afifi, Michel Marot

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2602.10048.json · badge: /api/ran/2602.10048.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
Mr-XcHan/FGO canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
are_equal_under_sympy Ran
ran, violated the contract we drafted
Mr-XcHan/FGO/src/open_r1/grader.py
pointer only (licence: NONE) · get_code("bc7ab5cea18531ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

count_unknown_letters_in_expr Ran
ran, honoured the contract we drafted
Mr-XcHan/FGO/src/open_r1/grader.py
pointer only (licence: NONE) · get_code("368d3db6347269c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

merge Ran
ran, honoured the contract we drafted
Mr-XcHan/FGO/src/open_r1/gpg_trainer.py
pointer only (licence: NONE); the stored copy get_code serves, from amap-ml/gpg, is pointer only (licence: NONE) · get_code("039728581d8123a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

merge_with_padding Ran
ran, honoured the contract we drafted
Mr-XcHan/FGO/src/open_r1/gpg_trainer.py
pointer only (licence: NONE); the stored copy get_code serves, from amap-ml/gpg, is pointer only (licence: NONE) · get_code("82e5778ec4883942")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

pad_sequence_to_length Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Mr-XcHan/FGO/src/open_r1/gpg_trainer.py
pointer only (licence: NONE); the stored copy get_code serves, from amap-ml/gpg, is pointer only (licence: NONE) · get_code("f7cb83c9a6b015a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

should_allow_eval Ran
ran, violated the contract we drafted
Mr-XcHan/FGO/src/open_r1/grader.py
pointer only (licence: NONE) · get_code("95f02454eddf082a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Mr-XcHan/FGO 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 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
should_allow_eval 13 other papers
8 dated earlier, 5 later
2305.20050 (2023-05)
Let's Verify Step by Step
2406.12809 (2024-06)
Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
2502.06703 (2025-02)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
and 10 more not named here
count_unknown_letters_in_expr 12 other papers
7 dated earlier, 5 later
2305.20050 (2023-05)
Let's Verify Step by Step
2502.06703 (2025-02)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
2503.10460 (2025-03)
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
and 9 more not named here
are_equal_under_sympy 4 other papers
1 dated earlier, 3 later
2305.20050 (2023-05)
Let's Verify Step by Step
2604.04356 (2026-04)
REAM: Merging Improves Pruning of Experts in LLMs
2605.10195 (2026-05)
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
and 1 more not named here
merge 1 other paper
1 dated earlier
2504.02546 (2025-04)
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
merge_with_padding 1 other paper
1 dated earlier
2504.02546 (2025-04)
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
pad_sequence_to_length 1 other paper
1 dated earlier
2504.02546 (2025-04)
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

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) often generate unnecessarily verbose Chain-of-Thought (CoT) reasoning that increases computational costs and latency without proportional performance gains. In this paper, we propose Fine-grained Group policy Optimization (FGO), a Reinforcement Learning (RL) algorithm that refines group responses by subdividing them and assigning appropriate weights based on length and entropy, thereby enabling effective CoT compression. Meanwhile, as an enhanced variant of Group Relative Policy Optimization (GRPO), FGO successfully addresses two major limitations of the GRPO: inefficient data utilization and entropy collapse. We evaluate FGO on multiple reasoning LLMs and benchmarks, including MATH500, AIME24, AMC23, and Minerva. Experimental results show that FGO achieves efficient CoT compression without degrading performance, and simultaneously resolves the key limitations of GRPO. Code: https://github.com/Mr-XcHan/FGO.

For agents

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

get_harvested_code_for_paper("2602.10048")
get_code_for_paper("2602.10048")
have("2602.10048")

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

curl https://syntology.ai/api/ran/2602.10048.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.10048.svg)](https://syntology.ai/paper/2602.10048)

Connect an agent — have() is free.