Papers › Can Textual Gradient Work in Federated Learning?

Can Textual Gradient Work in Federated Learning?

27 Feb 2025arXiv:2502.19980archive 2025-07-28

Minghui Chen, Ruinan Jin, Wenlong Deng, YuanYuan Chen, Zhi Huang, Han Yu, Xiaoxiao Li

Recent studies highlight the promise of LLM-based prompt optimization, especially with TextGrad, which automates differentiation'' via texts and backpropagates textual feedback. This approach facilitates training in various real-world applications that do not support numerical gradient propagation or loss calculation. In this paper, we systematically explore the potential and challenges of incorporating textual gradient into Federated Learning (FL). Our contributions are fourfold. Firstly, we introduce a novel FL paradigm, Federated Textual Gradient (FedTextGrad), that allows clients to upload locally optimized prompts derived from textual gradients, while the server aggregates the received prompts. Unlike traditional FL frameworks, which are designed for numerical aggregation, FedTextGrad is specifically tailored for handling textual data, expanding the applicability of FL to a broader range of problems that lack well-defined numerical loss functions. Secondly, building on this design, we conduct extensive experiments to explore the feasibility of FedTextGrad. Our findings highlight the importance of properly tuning key factors (e.g., local steps) in FL training. Thirdly, we highlight a major challenge in FedTextGrad aggregation: retaining essential information from distributed prompt updates. Last but not least, in response to this issue, we improve the vanilla variant of FedTextGrad by providing actionable guidance to the LLM when summarizing client prompts by leveraging the Uniform Information Density principle. Through this principled study, we enable the adoption of textual gradients in FL for optimizing LLMs, identify important issues, and pinpoint future directions, thereby opening up a new research area that warrants further investigation.

PaperPDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 1 repository linked to this paper: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 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: 12 samples from 1 repository, 6 ran (3 with no instrument failure; 3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ubc-tea/FedTextGrad officialmentioned on GitHubSyntology: 12 samples, 6 ran (3 instrument-failed) · 6 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

12 samples harvested: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 6 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.

2ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
1ran
6unverified

Licence: 12 of the 12 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 ubc-tea/FedTextGrad. “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.

ubc-tea/FedTextGrad official repository 12 samples, 6 ran (3 instrument-failed) · 6 unverified
SingletonBackwardEngine textgrad/optimizer/optimizer.py ran no licence file found · pointer only · 5008a349531d9698 · report fixture: returned SingletonBackwardEngine · level recorded 2026-09-22
_check_if_multimodal textgrad/optimizer/optimizer.py ran · violated contract no licence file found · pointer only · 6c6b64c6f227a73e · report fixture: signature engine_name:str/0/str · returned bool · level recorded 2026-09-22
construct_tgd_prompt textgrad/optimizer/optimizer.py ran · our draft was wrong no licence file found · pointer only · 792feffeafa114cd · report fixture: signature do_momentum:bool/0/bool, do_constrained:bool/0/bool, do_in_context_examples:bool/0/bool, variable_desc:str/0/str, variable_short:str/0/str, variable_grad:str/0/str, past_values:str/0/str, constraint_text:str/0/str, in_context_examples:str/0/str, new_variable_start_tag:str/0/str, new_variable_end_tag:str/0/str · returned str · level recorded 2026-09-22
get_gradient_and_context_text textgrad/optimizer/optimizer.py ran · our draft was wrong no licence file found · pointer only · ce12de8593347921 · report fixture: signature variable:Variable/0/? · returned str · level recorded 2026-09-22
is_valid_url textgrad/optimizer/optimizer.py ran · violated contract no licence file found · pointer only · a5790751e1d60937 · report fixture: signature url:str/0/str · returned bool · level recorded 2026-09-22
validate_engine_or_get_default textgrad/optimizer/optimizer.py ran; the contract check could not run (DEP_MISSING) no licence file found · pointer only · 1bebe4ea01268cce · report fixture: signature engine:callable/0/? · returned ConcreteEngineLM · level recorded 2026-09-22
EngineLM textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · 4742d5b210b29ae7 · report
Optimizer in 18 papers textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · 564ea28ae44d788f · report
TextualGradientDescent textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · 37c7ec07ab37ca27 · report
_backward_idempotent textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · 6facfd654eb7db2e · report
_check_and_reduce_gradients textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · b40994628dd26d87 · report
get_engine textgrad/optimizer/optimizer.py unverified no licence file found · pointer only · d0b6421efc2f659d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Federated Textual Gradient (FedTextGrad) (graph method: Federated Textual Gradient (FedTextGrad)). 12 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. TextualGradientDescent entry · level 0 · unverified · 37c7ec07ab37ca27
  2. EngineLM model · level 0 · unverified · 4742d5b210b29ae7
  3. Optimizer helper · level 0 · unverified · 564ea28ae44d788f
  4. construct_tgd_prompt helper · level 1 · ran · our draft was wrong · 792feffeafa114cd
  5. get_gradient_and_context_text helper · level 1 · ran · our draft was wrong · ce12de8593347921
  6. validate_engine_or_get_default helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 1bebe4ea01268cce
  7. SingletonBackwardEngine helper · level 1 · ran · 5008a349531d9698
  8. get_engine helper · level 0 · unverified · d0b6421efc2f659d
  9. _check_if_multimodal helper · level 1 · ran · violated contract · 6c6b64c6f227a73e
  10. _backward_idempotent helper · level 0 · unverified · 6facfd654eb7db2e
  11. _check_and_reduce_gradients helper · level 0 · unverified · b40994628dd26d87
  12. is_valid_url helper · level 1 · ran · violated contract · a5790751e1d60937

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2502.19980") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Federated Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

TextGrad

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