Pith.

Artificial Intelligence · arXiv:2610.21348 v1 · submitted 15 Oct 2026 · 42 references

FedSkillGit: Federated Skill Evolution via Version Control

Boxun Lan, Jiamei Li, Weijian Li, Chengyu Yang, Zhuang Qi, Chengcheng Wan, Xiaohong Chen, Ming Hu

The paper says

“Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution.”

more of the abstract

The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation. That design is poorly matched to skill evolution for three reasons. An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in a document that the server cannot meaningfully attribute. We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits. Each participating client submits a bounded set of patches over named rules together with its local experience, which summarizes what the round taught it, and the pair passes a two-stage privacy filter before it leaves the client. The server deduplicates the submitted patches and the local experience of all participants, updates a global experience document that only the optimizers read, and merges the surviving patches into a candidate skill. The candidate is distributed to the clients, which score it on their own validation sets and report the results, and it is published only when the reported scores improve on the current version. Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 16 Oct 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up, with conditions. A well-designed federated skill-evolution protocol with honest limitations, but the evidence for its central claim rests on single-run cells without variance — worth reading, but needs stronger empirical grounding before publication. This line is wrong

3 major objections · 6 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 42 references say.

The paper says, at Section IV and Appendix C

The review did not quote this passage.

Pith says: Objection 1 of 3 · major

All experimental results are based on a single run per cell (one fixed client partition, one fixed participation schedule, one seed document; see Appendix C). No variance, standard deviation, or confidence interval is reported. The central claims—that FedSkillGit 'exceeds Independent in all nine cells' and 'lands within a median gap of -0.8'—are stated as deterministic comparisons.

more of objection 1

Given the inherent non-determinism of LLM-based executor, optimizer, and merge agents, single runs cannot certify ordering, especially for margins as small as 0.8–1.6 percentage points (e.g., GPT-5.4-mini, LiveMath: 28.8 vs 28.8; SearchQA: 78.6 vs 77.5). The authors should report results from multiple independent runs (at least 5) and provide standard deviations or confidence intervals. Without this, the empirical support for the main conclusions is insufficient.

The paper says, at Abstract and Contribution (b9, b139)

The review did not quote this passage.

Pith says: Objection 2 of 3 · major

The abstract and contribution bullet claim that FedSkillGit 'outperforms state-of-the-art baselines by up to 22%'. I was unable to locate a 22% relative improvement in Table I. The largest absolute gain over Independent is 10.1 points (Gemini3-flash, SearchQA: 87.3 vs 77.2), which is a 13.1% relative improvement. The 22% claim appears unsupported. Please specify the exact baseline and cell that yields this number, or correct the claim.

The paper says, at Section II-C and IV-A

The review did not quote this passage.

Pith says: Objection 3 of 3 · major

The paper discusses FederatedSkill [42] as the most closely related prior work on federated skill evolution but does not include it as an experimental baseline. While the authors motivate the difference in objective (personalized vs. shared skill), a comparison under a shared-skill variant or at least a discussion of why it cannot be included would strengthen the claim of outperforming 'state-of-the-art baselines'. As it stands, the evaluated baselines (Independent, DocMerge, No Skill) are self-constructed.

6 minor objections

The paper says, at Abstract and Conclusion

Pith says: minor objection 1 of 6

The phrase 'state-of-the-art baselines' is imprecise. The paper compares only against self-constructed baselines; suggest rephrasing to 'naturally constructed baselines' or specifying the baselines explicitly.

The paper says, at Table I

Pith says: minor objection 2 of 6

The text mentions that 'by family average it leads on GPT-5.4-mini by +0.4', but these family averages are not shown in the table. Consider adding a row for the average per model family.

show 4 more

The paper says, at Figures 2 and 3

Pith says: minor objection 3 of 6

These figures report only convergence rounds. To assess scalability meaningfully, the final task success rate should also be reported for each configuration, to confirm that performance is maintained as the number of clients or participation ratio varies.

The paper says, at Eq. (7)

Pith says: minor objection 4 of 6

The symbol Match(v, c) is defined but not used elsewhere. Clarify that Match is an exact string-matching function (e.g., substring match).

The paper says, at Appendix A

Pith says: minor objection 5 of 6

The prompts assume that LLMs will reliably follow detailed instructions. Given known prompt sensitivity, the authors should note that the results may depend on prompt wording and that a prompt-sensitivity analysis would strengthen robustness.

The paper says, at b258–b262

Pith says: minor objection 6 of 6

The authors honestly acknowledge that privacy is enforced on the payload, not against inference. This is appropriate. However, the privacy ablation (Table III) measures only first-pass audit rate, not actual information leakage. Consider adding a small adversarial analysis or stating this as a limitation more explicitly in the main text (not just the appendix).

What would settle it

Rerun the GPT-5.4-mini condition on SearchQA and LiveMath (the two tightest cells) with at least five independent seeds, resampling the client partition, the participation schedule, and LLM sampling, holding the seed document and per-round budget fixed. For each cell report the mean and a paired interval for FedSkillGit-minus-Independent and FedSkillGit-minus-DocMerge. Decision rule: if any interval for FedSkillGit-minus-Independent includes zero, the "exceeds Independent in all nine cells" and "mean gain of +4.3" statements must be restated with uncertainty; if any FedSkillGit-minus-DocMerge interval includes zero, the "trails in all nine cells" claim and the 22% figure lose their basis. If all intervals stay strictly positive, the concern does not land and the current wording is defensible.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 16 Oct 2026

  1. Reader holds up, with conditions confidence high
  2. Skeptic partly agrees 2 min 16 s · 17,015 tokens read, 12,651 written
  3. Editor wrote the verdict above 16 s · 18,110 tokens read, 982 written
  4. Referee major revision: 3 major objections, 6 minor 29 s · 17,545 tokens read, 2,762 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

This paper proposes FedSkillGit, a protocol that replaces full-document uploads with rule-level commits, two-stage privacy filtering, and a global experience document. The motivation is solid: standard federated learning is a bad fit for natural-language skill artifacts, and version-control concepts are a natural alternative. The authors spell out their design choices clearly, run ablations, and include an unusually candid limitations appendix. Credit where due: they know what they didn't solve, and they say it.

The soft spot is inferential, not conceptual. The headline claims — outperforming independent evolution by 4.3 points on average, landing within 0.8 of centralized — are arithmetically correct but supported by exactly one run per cell (Appendix C). Several cells are decided by gaps of 1.6 and 0.8 points. At that resolution, a single seed partition, one fixed participation schedule, and the non-determinism of the LLM callers mean I cannot tell whether these ordering are real. The abstract's 'up to 22%' is a relative gain over DocMerge, a self-constructed single-shot baseline; the one published federated-skill baseline (FederatedSkill) is discussed but not run. That's a missing comparison that matters.

The privacy mechanism remains heuristic (the authors acknowledge this: payload-only enforcement, no inference guarantee), which is fine for a systems paper but should be framed less prominently. The code is not shipped, and the runs are not reproducible beyond the description.

Who this is for: researchers building federated agentic systems who want a concrete protocol to start from. It is a useful template, not a final result. A serious referee should see this paper — the idea is new enough and the design is careful — but should ask for variance estimates, more runs, and at least a comparison to FederatedSkill on the same setting. I would accept peer review for this paper conditional on major revision.

The strongest objection

The central claim has three legs: (i) FedSkillGit beats Independent in all nine cells by a mean of +4.3, (ii) it lands within a median -0.8 of Centralized, (iii) raw client data never leaves. Leg (iii) is honest about its own bounds (b258–b262 acknowledge payload-only enforcement, server-visible commits, and no inference guarantee), so I set it aside per the acknowledgement rule. Legs (i) and (ii) are arithmetically correct: I recomputed all nine FedSkillGit-minus-Independent gaps (2.5, 1.6, 5.7, 2.3, 4.0, 1.6, 10.1, 8.8, 1.7; mean 4.26) and all nine minus-Centralized gaps (median -0.8, mean -1.0). The load-bearing problem is inferential, not numerical. Appendix C reports a single run per cell with one fixed client partition, one fixed participation schedule, and one seed document; no variance, seed count, or interval is reported. Two of the four comparisons that carry the narrative are decided by sub-2-point differences: GPT-5.4-mini/LiveMath has FedSkillGit 28.8, Centralized 28.8, DocMerge 28.0, Independent 27.2, and GPT-5.4-mini/SearchQA has 78.6 vs 77.5 vs 76.1. At that spacing, "exceeds Independent in all nine cells" (b139) and "DocMerge trails in all nine cells" (b142) assert a strict ordering the design cannot yet certify, because the uncontrolled variance is run-level (sampling non-determinism of executor, optimizer, and merge agents, plus schedule order), and pairing on items within a run does not remove it. Relatedly, the abstract and contribution bullet advertise "outperforms state-of-the-art baselines by up to 22%"; no percentage is derived anywhere in the body, and the figure is reconstructible only as the Gemini3-flash/LiveMath relative gain over DocMerge (40.0 vs 32.8 = +22.0%), a self-constructed single-shot-merge baseline, while the one published federated skill-evolution system, FederatedSkill [42], is not run.

The reader's verdict (CONDITIONAL, HIGH confidence) and its two stated grounds are reasonable, and I would keep the verdict where it is. Where I differ is emphasis. The reader's weakest_assumption targets the reliability of the LLM optimizer and merge agents (Appendices A.B and A.C). That is a real mechanism, but it is partly self-controlling for the comparative claim: both FedSkillGit and DocMerge use "a strong optimizer" and the same merge machinery where an aggregation step exists (Appendix C-d), so a weak merge agent degrades the treatment and the closest baseline together, and Table II already ablates the experience document's two roles. The more load-bearing gap is one level up, in the evidence base for the aggregate statistics that the strongest_claim is built from: nine single-run cells, no seed sweep, no intervals, with the decisive comparisons at 0.8–1.6 points in two cells. A single run cannot distinguish a 1.6-point gain from run-to-run variation in an LLM-agent loop, yet the paper's language asserts a strict nine-for-nine ordering, and the abstract's "up to 22%" is a relative percentage over one cell of a baseline the authors built rather than the published federated method they themselves identify as closest in Related Work II-C. Credit where due: the arithmetic is internally consistent (I verified the mean +4.3, the median -0.8, the -0.8 to -5.1 Centralized range, and the +0.8 to +7.2 DocMerge range against Table I); the family averages that qualify the Centralized comparison are disclosed in b141 rather than hidden; the limitations appendix is unusually candid on the single-document trade, the validation-cost assumption, payload-level privacy, server visibility, and population growth cost; and the no-skill reference in every row is a useful control. Nothing here indicates an error, and none of it justifies REJECT. My recommendation is therefore UNCHANGED, with one condition worth adding to the existing CONDITIONAL: state the seed count and report per-cell dispersion for at least the two tightest cells, and either define the 22% figure in the body or scope the SOTA language to the constructed baselines. If the multi-seed gaps hold strictly positive, my concern does not land and the paper's current wording stands as written.

The referee's report

If the reported gains are statistically reliable, FedSkillGit introduces a principled way to federate the evolution of natural-language skill documents while preserving privacy at the payload level. The idea of using version-control-inspired commits rather than full-document uploads is novel in the federated LLM-agent setting, and the incorporation of a global experience document to guide both local optimization and merging is a plausible mechanism to reduce redundant exploration. The problem of collaborative skill evolution without sharing trajectories is practically relevant for multi-tenant deployments where data owners cannot pool raw data.

Pith's reading of the paper (a machine's summary, not the authors')

FedSkillGit is a framework for federated skill evolution that replaces full-document updates with fine-grained, privacy-filtered commits. Each client submits a bounded set of rule-level patches together with a local experience summary, both sanitized and audited before leaving the client. The server deduplicates, accumulates global experience to guide future revisions, merges surviving patches, and validates the candidate skill against client-held validation sets before publishing. If the approach works as claimed, it allows populations of LLM agents to pool their distributed learning without pooling their raw data, matching most of the benefit of centralized evolution across three datasets and three model families.

What carries the argument. The central mechanism is the commit-based skill update with two supporting structures: a global experience document and a two-stage privacy filter. A commit packages a bounded set of rule-level edits (append, insert-after, replace) together with a local experience summary. The global experience document accumulates failure patterns and rejected revisions from all prior rounds, is read only by the optimizer and merge agents, and reduces redundant exploration. The privacy filter first sanitizes free-text fields by replacing likely sensitive values with typed placeholders, then audits the result against a client's frozen private-value set, returning failed commits to the sanitizer for revision.

Core claim. The paper claims that exchanging structured commits rather than full documents solves three core problems of federated skill evolution: privacy leakage (commits are sanitized and audited), communication efficiency (only patches are transmitted), and attribution (each commit is traceable to its proposing client). The key experimental finding is that FedSkillGit outperforms independent evolution in all nine tested cells across SearchQA, LiveMath, and DocVQA using GPT-5.4-mini, Qwen3.5-flash, and Gemini3-flash, with gains between 1.6 and 10.1 percentage points (mean gain +4.3) and a median gap of −0.8 percentage points relative to centralized evolution, demonstrating that federated collaboration recovers most of the benefit of having all data in one place without sharing raw execution trajectories.

The premise it rests on. The LLM-based optimizer and merge agent (prompted in Appendix A) can reliably extract, generalize, and aggregate useful skill revisions from local execution trajectories and the global experience document without introducing systematic bias, hallucinating invalid patches, or failing to identify redundancies.

If the paper is right (Pith's inferences, not the authors')

Collaborative skill evolution can be deployed in privacy-sensitive multi-agent settings where raw execution data cannot be pooled, using the same LLM as both executor and optimizer.

The version-control abstraction (commits, merge, validation gate) provides a natural framework for auditing: which client contributed each revision and whether it persisted through validation is recorded by construction.

Convergence cost is predictable, rising with client count (5 rounds at 10 clients to 9 at 100) and falling with participation ratio (13 rounds at 10% to 3 at 50%), enabling deployment planning.

The global experience document reduces redundant knowledge exploration both locally and at the server, as shown by ablation: removing either role drops task success rate from 78.6% to 76.9% or 77.2% on SearchQA with GPT-5.4-mini.

Single-shot merging of full documents is not sufficient: the iterative DocMerge baseline trails FedSkillGit in all nine cells by between 0.8 and 7.2 percentage points.

The commit abstraction could extend beyond skill documents to any structured artifact agents maintain collaboratively—such as prompt libraries, tool definitions, or configuration files—where revisions are localized and semantically meaningful.

Because the publication gate validates against the union of client validation sets, an implicit assumption is that the validation data collectively covers the task distribution well; a client with a too-small or too-biased validation slice could cause harmful revisions to pass or good ones to be rejected.

The two-stage privacy filter addresses content leakage but not inference leakage (as the authors note); combining FedSkillGit with differential privacy or secure aggregation would be a natural next step, though it would need to preserve the structured-natural-language update abstraction.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution. The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation. That design is poorly matched to skill evolution for three reasons. An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in a document that the server cannot meaningfully attribute. We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits. Each participating client submits a bounded set of patches over named rules together with its local experience, which summarizes what the round taught it, and the pair passes a two-stage privacy filter before it leaves the client. The server deduplicates the submitted patches and the local experience of all participants, updates a global experience document that only the optimizers read, and merges the surviving patches into a candidate skill. The candidate is distributed to the clients, which score it on their own validation sets and report the results, and it is published only when the reported scores improve on the current version. Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-16

The authors' main claim, as the classifier picked it out 1.00

“Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.10 · states limitation 0.24 · human participants 0.09 · controlled comparison 0.91 · randomized assignment 0.02 · states quantitative result 0.98 · compares with prior results 0.98 · mentions code or data availability 0.04

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. background 1.00 0.09 0.03 hedged possibility 0.56
In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution. background 0.94 0.08 0.03 asserted 1.00
The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation. background 0.95 0.08 0.02 asserted 0.99
That design is poorly matched to skill evolution for three reasons. gap 0.55 0.21 0.03 asserted 0.99
An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in a document that the server cannot meaningfully attribute. background 0.61 0.20 0.06 asserted 0.97
We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits. contribution 0.95 0.79 0.13 asserted 0.99
Each participating client submits a bounded set of patches over named rules together with its local experience, which summarizes what the round taught it, and the pair passes a two-stage privacy filter before it leaves the client. method 0.97 0.72 0.06 asserted 0.99
The server deduplicates the submitted patches and the local experience of all participants, updates a global experience document that only the optimizers read, and merges the surviving patches into a candidate skill. method 0.99 0.74 0.05 asserted 0.98
The candidate is distributed to the clients, which score it on their own validation sets and report the results, and it is published only when the reported scores improve on the current version. method 1.00 0.80 0.08 asserted 0.96
Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data. result 1.00 0.96 0.84 asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 1.00

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-16: 1 request, 7,599 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (2)
Figure 1 of the paper
Figure 1. Overview of our proposed FedSkillGit. The framework consists of local skill evolution and server-side skill updating. Each selected client generates
Figure 2 of the paper
Figure 2. Convergence round count against the number of clients, with the participation ratio fixed at 30 % on GPT-5.4-mini and SearchQA. The count rises monotonically and the increase accelerates with popu￾lation size. 10 20 30 40 50 Participation ratio (%) 2 4 6 8 10 12 14 Convergence rounds 13 7 5 4 3

Figures are the authors', reproduced from the paper.

References (42)
  1. [42] J. Yang, G. Yao, Y . Zhang, R. R. Kompella, G. Liu, and S. Chang, “FederatedSkill: Federated learning for agentic skill evolution,”arXiv preprint arXiv:2606.03143, 2026. APPENDIXA PROMPTTEMPLATES OF THEPROTOCOL This appendix gives the prompt templates of FedSkillGit. The execu... on PithPith's reviewarXiv
  2. [1] Y . Yang, J. Li, Q. Pan, B. Zhan, Y . Cai, L. Du, J. Zhou, K. Chen, Q. Chen, X. Li, B. Zhang, and L. He, “Autoskill: Experience-driven life- long learning via skill self-evolution,”arXiv preprint arXiv:2603.01145, 2026 on PitharXiv
  3. [2] Y . Xiong, Z. Miao, Q. Chen, L. Li, Y . Wang, S. He, J. Zhao, and K. Liu, “Skillpyramid: A hierarchical skill consolidation framework for self- evolving agents,”arXiv preprint arXiv:2606.03692, 2026 on PithPith's reviewarXiv
  4. [3] Y . Yang, Z. Gong, W. Huang, Q. Yang, Z. Zhou, Z. Huang, Y . Li, X. Gao, Q. Dai, B. Liu, K. Qiu, Y . Yang, D. Chen, X. Yang, and C. Luo, “Skillopt: Executive strategy for self-evolving agent skills,” arXiv preprint arXiv:2605.23904, 2026 on PithPith's reviewarXiv
  5. [4] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. Ag ¨uera y Arcas, “Communication-efficient learning of deep networks from decen- tralized data,” inAISTATS 2017, 2017 on Pith
  6. [5] P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, R. G. L. D’Oliveira, H. Eichner, S. E. Rouayheb, D. Evans, J. Gardner, Z. Garrett, A. Gasc ´on, B. Ghazi, P. B. Gibbons, M. Gruteser, Z. Harchaoui, C. He... on Pith
  7. [6] M. Hu, Y . Cao, A. Li, Z. Li, C. Liu, T. Li, M. Chen, and Y . Liu, “FedMut: Generalized federated learning via stochastic mutation,” in AAAI Conference on Artificial Intelligence, 2024, pp. 12 528–12 537 on Pith
  8. [7] M. Hu, Z. Xia, D. Yan, Z. Yue, J. Xia, Y . Huang, Y . Liu, and M. Chen, “Gitfl: Uncertainty-aware real-time asynchronous federated learning using version control,” in2023 IEEE Real-Time Systems Symposium (RTSS). IEEE, 2023, pp. 145–157 on Pith
  9. [8] Z. Qi, L. Meng, and et al., “Cross-silo feature space alignment for federated learning on clients with imbalanced data,” inAAAI, 2025, pp. 19 986–19 994 on Pith
  10. [9] Z. Lu, C. Jia, M. Hu, X. Xie, and M. Chen, “Gradients as an action: Towards communication-efficient federated recommender systems via adaptive action sharing,” inProceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V . 2, 2025, pp. 1999–2009 on Pith
  11. [10] W. Huang, M. Ye, Z. Shi, G. Wan, H. Li, B. Du, and Q. Yang, “Federated learning for generalization, robustness, fairness: A survey and benchmark,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 9387–9406, 2024 on Pith
  12. [11] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V . Smith, “Federated optimization in heterogeneous networks,” inMLSys 2020, 2020 on Pith
  13. [12] S. P. Karimireddy, S. Kale, M. Mohri, S. J. Reddi, S. U. Stich, and A. T. Suresh, “Scaffold: Stochastic controlled averaging for federated learning,” inICML 2020, 2020 on Pith
  14. [13] T. Lin, L. Kong, S. U. Stich, and M. Jaggi, “Ensemble distillation for robust model fusion in federated learning,” inNeurIPS 2020, 2020 on Pith
  15. [14] M. Cao, T. Chen, M. Hu, Z. Qi, Y . Cui, J. Zhou, and X. Xie, “Two heads are better than one: Generalized cross-domain federated learning via dual-prototype,” inProceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V . 1, 2026, pp. 59–70 on Pith
  16. [15] L. Fu, S. Huang, Y . Lai, T. Liao, C. Zhang, and C. Chen, “Beyond federated prototype learning: Learnable semantic anchors with hyper- spherical contrast for domain-skewed data,” inProceedings of the AAAI Conference on Artificial Intelligence, 2025, pp. 16 648–16 656 on Pith
  17. [16] M. Hu, Z. Yue, X. Xie, C. Chen, Y . Huang, X. Wei, X. Lian, Y . Liu, and M. Chen, “Is aggregation the only choice? federated learning via layer-wise model recombination,” inProceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024, pp. 1096–1107 on Pith
  18. [17] M. Hu, P. Zhou, Z. Yue, Z. Ling, Y . Huang, A. Li, Y . Liu, X. Lian, and M. Chen, “Fedcross: Towards accurate federated learning via multi-model cross-aggregation,” inProceedings of IEEE International Conference on Data Engineering (ICDE). IEEE, 2024, pp. 2137–2150 on Pith
  19. [18] A. Fallah, A. Mokhtari, and A. Ozdaglar, “Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach,” inNeurIPS 2020, 2020 on Pith
  20. [19] C. T. Dinh, N. H. Tran, and T. D. Nguyen, “Personalized federated learning with moreau envelopes,” inNeurIPS 2020, 2020 on Pith
show 22 more
  1. [20] T. Nishio and R. Yonetani, “Client selection for federated learning with heterogeneous resources in mobile edge,” inIEEE ICC 2019, 2019 on Pith
  2. [21] C. Jia, M. Hu, Z. Chen, Y . Yang, X. Xie, Y . Liu, and M. Chen, “Adaptivefl: Adaptive heterogeneous federated learning for resource- constrained aiot systems,” inProceedings of ACM/IEEE Design Automa- tion Conference, 2024, pp. 1–6 on Pith
  3. [22] R. Liu, M. Hu, Z. Xia, X. Xie, J. Xia, P. Zhang, Y . Huang, and M. Chen, “Fedgraft: Memory-aware heterogeneous federated learning via model grafting,”IEEE Transactions on Mobile Computing, vol. 24, no. 12, pp. 13 506–13 519, 2025 on Pith
  4. [23] Z. Xia, M. Hu, D. Yan, R. Liu, A. Li, X. Xie, and M. Chen, “Multisfl: Towards accurate split federated learning via multi-model aggregation and knowledge replay,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 1, 2025, pp. 914–922 on Pith
  5. [24] R. Ju, X. Wang, X. Ding, Y . Yang, H. Wu, S. Jiang, Q. Zhang, H. Wen, X. Li, W. Wang, K. Li, Y . Liu, H. Dai, W. Wang, and T. Cao, “Embodiskill: Skill-aware reflection for self-evolving embodied agents,” arXiv preprint arXiv:2605.10332, 2026 on PithPith's reviewarXiv
  6. [25] H. Zhou, S. Guo, A. Liu, Z. Yu, Z. Gong, B. Zhao, Z. Chen, M. Zhang, Y . Chen, J. Li, R. Yang, Q. Liu, X. Yu, J. Zhou, N. Wang, C. Sun, and J. Wang, “Memento-skills: Let agents design agents,”arXiv preprint arXiv:2603.18743, 2026 on PitharXiv
  7. [26] G. Jiang, Z. Su, X. Qu, and Y . R. Fung, “Xskill: Continual learn- ing from experience and skills in multimodal agents,”arXiv preprint arXiv:2603.12056, 2026 on PithPith's reviewarXiv
  8. [27] Y . Liang, R. Zhong, H. Xu, C. Jiang, Y . Zhong, R. Fang, J.-C. Gu, S. Deng, Y . Yao, M. Wang, S. Qiao, Y . Xue, X. Xu, T. Wu, K. Wang, Y . Liu, Z. Bi, J. Lou, Y . E. Jiang, H. Zhu, G. Yu, H. Hong, L. Huang, H. Xue, C. Wang, Y . Wang, Z. Shan, X. Chen, Z. Tu, F. Xiong, X. Xie,... on PithPith's reviewarXiv
  9. [28] Y . Gao, Z. Li, Y . Yuan, Z. Ji, P. Ma, and S. Wang, “Skillre- ducer: Optimizing llm agent skills for token efficiency,”arXiv preprint arXiv:2603.29919, 2026 on PithPith's reviewarXiv
  10. [29] S. Tu, C. Xu, Q. Zhang, Y . Zhang, X. Lan, L. Li, D. Li, and D. Zhao, “Dynamic dual-granularity skill bank for agentic rl,”arXiv preprint arXiv:2603.28716, 2026 on PithPith's reviewarXiv
  11. [30] C. Wang, Z. Yu, X. Xie, W. Yao, R. Fang, S. Qiao, K. Cao, G. Zheng, X. Qi, P. Zhang, and S. Deng, “Skillx: Automatically constructing skill knowledge bases for agents,”arXiv preprint arXiv:2604.04804, 2026 on PithPith's reviewarXiv
  12. [31] S. Ouyang, J. Yan, Y . Chen, R. Han, Z. Wang, B. D. Mishra, R. Meng, C.-L. Li, Y . Jiao, K. Zha, M. Shen, V . Tirumalashetty, G. Lee, J. Han, T. Pfister, and C.-Y . Lee, “Skillos: Learning skill curation for self- evolving agents,”arXiv preprint arXiv:2605.06614, 2026 on PithPith's reviewarXiv
  13. [32] S. Shen, W. Cheng, M. Ma, A. Turcan, M. J. Zhang, and J. Ma, “Skill- foundry: Building self-evolving agent skill libraries from heterogeneous scientific resources,”arXiv preprint arXiv:2604.03964, 2026 on PithPith's reviewarXiv
  14. [33] X. Liu, X. Luo, L. Li, G. Huang, J. Liu, and H. Qiao, “Skillforge: Forging domain-specific, self-evolving agent skills in cloud technical support,” inProceedings of the 49th International ACM SIGIR Confer- ence on Research and Development in Information Retrieval, 2026 on Pith
  15. [34] Y . Tian, J. Chen, L. Zheng, M. Tao, X. Zeng, Z. Yin, H. Su, and X. Sun, “Skills-coach: A self-evolving skill optimizer via training-free grpo,” arXiv preprint arXiv:2604.27488, 2026 on PithPith's reviewarXiv
  16. [35] H. Zhang, S. Fan, H. P. Zou, Y . Chen, Z. Wang, J. Zhou, C. Li, W.-C. Huang, Y . Yao, K. Zheng, X. Liu, X. Li, and P. S. Yu, “Coevoskills: Self- evolving agent skills via co-evolutionary verification,”arXiv preprint arXiv:2604.01687, 2026 on PithPith's reviewarXiv
  17. [36] J. Ni, Y . Liu, X. Liu, Y . Sun, M. Zhou, P. Cheng, D. Wang, E. Zhao, X. Jiang, and G. Jiang, “Trace2skill: Distill trajectory-local lessons into transferable agent skills,”arXiv preprint arXiv:2603.25158, 2026 on PithPith's reviewarXiv
  18. [37] Y . Shi, Y . Chen, Z. Lu, Y . Miao, S. Liu, Q. GU, X. Cai, X. Wang, and A. Zhang, “Skill1: Unified evolution of skill-augmented agents via reinforcement learning,”arXiv preprint arXiv:2605.06130, 2026 on PithPith's reviewarXiv
  19. [38] P. Xia, J. Chen, H. Wang, J. Liu, K. Zeng, Y . Wang, S. Han, Y . Zhou, X. Zhao, H. Chen, Z. Zheng, C. Xie, and H. Yao, “Skillrl: Evolving agents via recursive skill-augmented reinforcement learning,”arXiv preprint arXiv:2602.08234, 2026 on PithPith's reviewarXiv
  20. [39] J. Wu, S. Yang, C. Yang, Y . Shen, S. Zhang, Z. Wen, and J. Tao, “Spark: Strategic policy-aware exploration via dynamic branching for long-horizon agentic learning,”arXiv preprint arXiv:2601.20209, 2026 on PithPith's reviewarXiv
  21. [40] Z. Ma, S. Yang, Y . Ji, X. Wang, Y . Wang, Y . Hu, T. Huang, and X. Chu, “Skillclaw: Let skills evolve collectively with agentic evolver,”arXiv preprint arXiv:2604.08377, 2026 on PithPith's reviewarXiv
  22. [41] S. Si, H. Zhao, Y . Lei, Q. Wang, D. Chen, Z. Wang, Z. Wang, K. Luo, Z. Wang, G. Chen, F. Qi, M. Zhang, and M. Sun, “From context to skills: Can language models learn from context skillfully?”arXiv preprint arXiv:2604.27660, 2026 on PithPith's reviewarXiv
Cited by 1 Pith paper

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment