Papers › Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent...

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

8 Oct 2024arXiv:2410.06101archive 2025-07-28

Hao Ma, Tianyi Hu, Zhiqiang Pu, Boyin Liu, Xiaolin Ai, Yanyan Liang, Min Chen

Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs. In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework, to leverage the inherent coevolution and emergent capabilities of multi-agent systems. In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer. The pioneer generates responses based on queries, while the observer generates responses using both the queries and the pioneer's responses. The two agents are trained together. During training, the agents exchange roles periodically, fostering cooperation and coevolution between them. Experiments evaluate CORY's performance by fine-tuning GPT-2 and Llama-2 under subjective and objective reward functions on the IMDB Review and GSM8K datasets, respectively. Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness, thereby underscoring its potential as a superior methodology for refining LLMs in real-world applications.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (3 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 8 samples that ran have no recorded date.

Harry67Hu/CORY officialmentioned on GitHubpytorchMITSyntology: 11 samples, 8 ran (5 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
2ran
3unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Harry67Hu/CORY. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Harry67Hu/CORY official repository 11 samples, 8 ran (5 instrument-failed) · 3 unverified
collator in 16 papers imdb_train/cory.py ran · our draft was wrong MIT (permissive) · bda36ad0c44dbd74 · report fixture: signature data:list/1/dict · returned dict · level recorded, date not recorded
convert_to_scalar in 24 papers trl/core.py ran · our draft was wrong MIT (permissive) · c32b636f13ed9ee5 · report fixture: signature stats:dict/0/? · returned dict · level recorded 2026-09-25
create_demo_text gsm8k_utils/gsm8k_utils.py ran · our draft was wrong MIT (permissive) · 5013cfeaf23a03ad · report fixture: signature n_shot:int/0/int, cot_flag:bool/0/bool · returned str · level recorded 2026-09-24
extract_answer_from_output in 7 papers gsm8k_utils/gsm8k_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 96fe095fcc6b821a · report fixture: signature completion:str/0/str · returned str · level recorded, date not recorded
is_correct in 12 papers gsm8k_utils/gsm8k_utils.py ran MIT (permissive) · e198da7bdc5637e3 · report fixture: signature model_answer:str/0/str, answer:str/0/str · returned bool · level recorded 2026-09-24
is_transformers_greater_than in 9 papers trl/import_utils.py ran · violated contract MIT (permissive) · f4334934ee795269 · report fixture: signature version:str/0/str · returned bool · level recorded 2026-09-25
respond_to_batch trl/models/model.py ran MIT (permissive) · 3fe7529a76b17e9c · report fixture: signature model:callable/0/?, source_ids:Tensor/2/int, attention_mask:Tensor/2/int, max_target_length:int/0/int, top_k:int/0/int, top_p:float/0/float · returned Tensor · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
trl/core.py ran; the contract check could not run (RAISES) MIT (permissive) · 5bcf8e086423cf6b · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-24
build_dataset in 151 papers gsm8k_utils/gsm8k_eval.py unverified MIT (permissive) · 0efa9af73116efc0 · report
flatten_dict in 72 papers trl/core.py unverified MIT (permissive) · a51ae45a1f6c0b5b · report
scheduler_step in 5 papers trl/models/modeling_sd_base.py unverified MIT (permissive) · 59046fe10dd792f4 · report

Tasks

GSM8KMulti-agent Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutEntropy RegularizationGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPPOResidual ConnectionSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections