Papers › OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration

OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration

17 May 2025arXiv:2505.11765archive 2025-07-28

Shijun Li, Hilaf Hasson, Joydeep Ghosh

Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other, have exhibited enhanced capabilities in complex tasks, such as high-quality code generation and arithmetic reasoning. However, the development of such systems often relies on handcrafted methods, and the literature on systematic design and optimization of LLM-based MAS remains limited. In this work, we introduce OMAC, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on code generation, arithmetic reasoning, and general reasoning tasks against state-of-the-art approaches.

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

The archive's official repository (xiwenchao/omac-demo) was not harvested; the 15 samples below come from 1 repository the archive does not mark official.

Syntology 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 15 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xiwenchao/omac-demo officialmentioned in paperMITSyntology: not harvested 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 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 has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
9ran
3unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xiwenchao/OMAC. “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.

xiwenchao/OMAC found in paper text by Syntology 15 samples, 12 ran (2 instrument-failed) · 3 unverified
calculate_score in 15 papers code/MMLU/calc_score.py ran MIT (permissive) · a7d74bc4eba65949 · report fixture: signature RES_DIR:str/0/str, EXP_NAME:str/0/str, TARGET_CSV:str/0/str · returned float64 · level recorded 2026-09-25
construct_assistant_message code/MATH/listwise_math.py ran MIT (permissive) · 97949d1f50cd1e53 · report fixture: signature completion:dict/0/? · returned dict · level recorded 2026-09-25
construct_judge_message code/HumanEval/prompt_lib.py ran MIT (permissive) · 10cf0920c5efdb39 · report fixture: signature responses:list/1/empty, question:str/0/str, qtype:str/0/str, role:str/0/str · returned dict · level recorded 2026-09-25
construct_message in 6 papers code/HumanEval/prompt_lib.py ran MIT (permissive) · 768aa810b639c13e · report fixture: signature responses:list/1/empty, question:str/0/str, qtype:str/0/str · returned dict · level recorded 2026-09-25
construct_message in 6 papers code/MATH/listwise_math.py ran MIT (permissive) · ff195fa5698279c2 · report fixture: signature agents:list/1/list, question:str/0/str · returned dict · level recorded 2026-09-25
construct_ranking_message code/HumanEval/prompt_lib.py ran MIT (permissive) · d8d506bb4d6eb83a · report fixture: signature responses:list/1/str, question:str/0/str, qtype:str/0/str, rank_prompt:str/0/str, max_agents:int/0/int · returned dict · level recorded 2026-09-25
construct_structure_message code/MATH/prompt_lib.py ran MIT (permissive) · 7ec82a253737d0da · report fixture: signature current_agent:list/1/dict, agents_to_select:list/1/list, structure_prompt:str/0/str · returned str · level recorded 2026-09-25
parse_bullets code/MATH/evol_eval_math.py ran · our draft was wrong fingerprinted MIT (permissive) · 52487c571369c8c3 · report fixture: signature sentence:str/0/str · returned list · level recorded 2026-09-22
parse_ranks code/HumanEval/utils.py ran MIT (permissive) · 2861b77fe609900a · report fixture: signature completion:str/0/str, max_num:int/0/int, random_num:int/0/int · returned list · level recorded 2026-09-25
parse_ranks code/MATH/prompt_lib.py ran fingerprinted MIT (permissive) · 292858f6b6362eab · report fixture: signature completion:str/0/str, max_num:int/0/int, random_num:int/0/int · returned int · level recorded 2026-09-25
parse_yes_no in 5 papers code/MATH/evol_eval_math.py ran · violated contract MIT (permissive) · efece58874c297b1 · report fixture: signature string:str/0/str · returned bool · level recorded 2026-09-22
solve_math_problems code/MATH/evol_eval_math.py ran · our draft was wrong fingerprinted MIT (permissive) · 8fce0277228f26b2 · report fixture: signature input_str:str/0/str · returned str · level recorded 2026-09-22
calculate_score in 15 papers code/HumanEval/utils_evo.py unverified MIT (permissive) · 23694908a81661df · report
construct_prerank_message code/MATH/prompt_lib.py unverified MIT (permissive) · 19fbbb08c4288bbc · report
construct_ranking_message code/MATH/listwise_math.py unverified MIT (permissive) · 0280292f0bc4da2c · report

Tasks

Arithmetic ReasoningCode Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MAS

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