Artificial Intelligence · arXiv:2609.38024 v1 · submitted 29 Sep 2026 · 18 references
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
The paper says
“An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness.”
more of the abstract
Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbfRetrieval-Augmented Skill Optimization (RASO), a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbfRetrieval-Augmented Skill Initialization (RASI) constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbfRetrieval-Augmented Skill Update (RASU) iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 30 Sep 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. Solid method advance with unusually careful experiments; the one real gap is the unreleased, unaudited contamination blocklist, which currently keeps the headline claim from being falsifiably separated from memorized benchmark content. This line is wrong
3 major objections · 5 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 18 references say.
The paper says, at §A.1, Fig. 4, Table 1
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.87):
“Since the external skill corpus is collected from public repositories, it may contain skills written specifically for our evaluation benchmarks.”
Pith says: Objection 1 of 3 · major
The load-bearing control for the claim that RASO's gains reflect transferable cross-harness knowledge is the per-benchmark keyword blocklist in §A.1, which is neither released nor evaluated for precision or recall. Because the central interpretation of the RASI/RASU margins (e.g., +11.30 on WebShop for Qwen-3.5-9B, Table 1) is that they come from adapting diverse external procedural knowledge rather than from retrieved …
more of objection 1
… target-solution content, the authors should release the blocklist, quantify residual leakage into the retrieval index (e.g., by sampling non-blocklisted repositories for benchmark-specific tasks), and ideally re-run the RASI-vs-RFSI isolation with the corpus restricted to sections explicitly flagged as non-matching. The corpus-size ablation in Fig. 4 varies the fraction of repositories while keeping all non-blocklisted ones, so it cannot detect residual contamination; the authors acknowledge this risk in sentence [b245] but do not measure it.
The paper says, at §5.2, Fig. 3
The review did not quote this passage.
Pith says: Objection 2 of 3 · major
The choice of K=5 is motivated by Figure 3, which plots performance against K, but the figure caption and the surrounding text do not state whether the curves report validation or test performance on OfficeQA and SpreadsheetBench. If K was selected using test-set results, then the main-table numbers inherit test-set-tuned hyperparameters and the reported margins are optimistic.
more of objection 2
The authors should state which split Figure 3 reports and, if it is the test split, either re-select K on D_val or report the sensitivity of the reported results to K across all four benchmarks.
The paper says, at §5.1, Table 1
The review did not quote this passage.
Pith says: Objection 3 of 3 · major
Several headline margins are small relative to the reported standard errors over only three seeds, e.g., ALFWorld 74.13±1.00 vs 72.64±0.90 and WebShop 46.61±0.11 vs 45.54±0.35 for GPT-5.6-Luna, and the paper reports no significance testing. The bold 'consistently outperforms' claim in the abstract and conclusion therefore rests more heavily than acknowledged on the large-margin benchmarks (SpreadsheetBench, OfficeQA, and WebShop with Qwen-3.5-9B).
more of objection 3
Reporting per-benchmark significance (e.g., paired bootstrap or a paired test across seeds) or explicitly flagging the margins that fall within one standard error would make the claim's strength transparent without contradicting the core results.
This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.
5 minor objections
The paper says, at §A.1
Pith says: minor objection 1 of 5
The blocklist is described only as matching 'the benchmark name and the names of the datasets it is built on'; publishing the exact keyword list would let readers assess recall and reproduce the corpus construction.
The paper says, at Appendix
Pith says: minor objection 2 of 5
No code, prompts, or retrieval index are released. Given that the RASI/RFSI and RASU-vs-baseline comparisons hinge on prompt and retrieval details, a public release (including the blocklist) is needed for the empirical claims to be verifiable.
show 3 more
The paper says, at Abstract
Pith says: minor objection 3 of 5
The abstract's phrasing 'consistently outperforms baselines without retrieval-augmented skill initialization and updating' should name the baseline set (TextGrad, GEPA, SkillOpt, WikiSkill under RFSI initialization) to avoid over-generalization.
The paper says, at Table 1
Pith says: minor objection 4 of 5
The model labels (GPT-5.6-Luna, Qwen-3.5-9B) appear as the final row of each block rather than as grouped headers, making the table harder to read; restructuring the panel headers would aid comprehension.
The paper says, at §A.5
Pith says: minor objection 5 of 5
The statement that RASO remains 'within $0.06 of the cheapest method on SpreadsheetBench' should be stated with the exact numbers (0.49 vs 0.43 USD) for clarity.
What would settle it
Request or independently reconstruct the per-benchmark blocklists and rerun RASI initialization (and one RASU iteration) on SpreadsheetBench and WebShop with two retrieval settings: (i) the full non-blocklisted corpus, and (ii) a corpus restricted to sections whose repository mentions neither the benchmark name nor its dataset name nor any known solution-hinting strings (e.g., answer headers, expected-output patterns). If the restriction removes sections that resemble target-solution code and the RASI/RASU margin over RFSI collapses or reverses, the central claim must be revised. A cheaper first check: release the blocklists and compute, per benchmark, the fraction of the retrieved top-5 sections that contain the benchmark or dataset name, reporting a residual-leakage statistic, and the performance deltas when those sections are removed.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 30 Sep 2026
- Reader holds up, with conditions
- Skeptic agrees
- Editor wrote the verdict above
- Referee major revision: 3 major objections, 5 minor
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
Two things to know. First, this is a genuinely useful method paper: putting retrieval-augmented initialization (RASI) and retrieval-augmented iterative update (RASU) together with cross-harness adaptation is a real combination that none of the cited works — SkillRouter, AgentKB, TextGrad, GEPA, SkillOpt, WikiSkill — operate jointly. Second, the one unclosed hole is retrieval-corpus contamination, and it is the load-bearing one.
Where it earns credit. The experimental hygiene is better than typical for this subfield. Rollout counts are matched across methods (Table 10), cost tables are reported honestly, and the fixed-initialization comparisons in the appendix (Tables 6-8) isolate the update procedure from the initialization. The RASI-vs-RFSI contrast in A.1 is clean by design: identical task/harness descriptions, identical procedure decomposition, identical initialization prompt — only retrieval and adaptation differ. The ablations in Table 2 show retrieval helps at both stages independently and additively. Updates are accepted only on held-out validation, K=5 was tuned on validation, and seed variance is reported. The authors openly state the contamination risk (b245: the corpus 'may contain skills written specifically for our evaluation benchmarks') and describe their repository-level blocklist.
Where it is soft. The blocklist is the whole mitigation and it is not yet verifiable: unreleased, manual, unmeasured for precision or recall, with no residual-leakage audit. Fig. 4 varies corpus fraction but keeps all non-blocklisted repositories, so it cannot detect residual leakage. That means the headline margins — especially +11.30 on WebShop for Qwen — are not yet distinguishable between transferable cross-harness procedural knowledge and retrieved benchmark-solution snippets. Because the authors chose repository-level exclusion specifically to catch skills that evade keyword matching, this is an honest, acknowledged risk; I do not read it as a credibility problem, but until the blocklist ships with a residual-leakage check, the central interpretation is not falsifiably supported. The qualitative example (Fig. 5) is a single case — it shows the mechanism on one instance, not across the margins.
Bottom line. This deserves a serious referee. The condition is narrow and fixable: release the blocklist, audit residual leakage (e.g., post-filter retrieval hit-rates on sections mentioning benchmark names), and ideally add an ablation restricting the corpus to confirmed non-matching sections. If that survives, the central claim holds. I would accept conditional on exactly that.
The strongest objection
RASI and RASU gains are claimed to reflect transferable procedural knowledge (e.g., the satellite-imagery boolean-mask lesson adapted to SpreadsheetBench in Fig. 5). For that claim to hold, retrieved sections must not encode evaluation-specific content. The authors themselves flag this in §A.1: "Since the external skill corpus is collected from public repositories, it may contain skills written specifically for our evaluation benchmarks." Their sole control is a per-benchmark keyword blocklist that is not released, not measured for precision or recall, and not audited for residual leakage. Three consequences follow. First, repositories that do not name a benchmark but contain its tasks evade keyword matching, as the authors acknowledge when choosing repository-level exclusion. Second, no ablation restricts the corpus to only non-matching sections: Fig. 4 varies corpus size but keeps all non-blocklisted repositories, so it cannot detect residual contamination. Third, the RASI-vs-RFSI isolation in §A.1 is clean in design but depends entirely on the blocklist being complete; if it is not, the RASI/RASU margins (e.g., +5.61 on OfficeQA, +11.30 on WebShop for Qwen-3.5-9B) could come from retrieving target-solution snippets rather than from cross-harness adaptation. The threat is not that the cited public corpus is suspect, but that the central interpretation—"adapting diverse external knowledge rather than relying on particular source documents" (§1 contributions)—is currently indistinguishable from memorized benchmark solutions. This is a correctness and interpretation risk, not an ad hominem: the authors honestly acknowledge the potential contamination and state a mitigation; what is missing is a released blocklist and a residual-leakage measurement that would make the claim falsifiable. I am not attacking the cost claims (Tables 9–10) or the matched-rollout comparison (Table 10), which are well supported and orthogonal.
The reader's weakest_assumption—residual leakage of evaluation-specific skills from GitSkills—is the single concern most likely to invalidate the paper's central claim that RASI and RASU gains come from transferable cross-harness procedural knowledge. I agree with this identification because the paper itself states in §A.1 that the corpus may contain benchmark-specific skills, and its only control is an unreleased, unmeasured keyword blocklist. The paper's other components are strong: the RASI-vs-RFSI isolation in §A.1 is a well-designed attempt to attribute the gain to retrieval, the ablations in Tables 2–4 cleanly separate initialization and update effects, and the matched-rollout and cost tables (Tables 9–10) directly address the practical-efficiency objection. I found no internal inconsistency, no unsupported cited theorem, and no fabricated evidence. The remaining load-bearing gap is entirely empirical: without a released blocklist and a residual-leakage audit, the central interpretation is not falsifiable. If the blocklist is released and a residual-leakage audit shows negligible contamination, the central claim would hold as stated; if not, the interpretation changes. Therefore the reader's CONDITIONAL verdict is appropriate, and I recommend no change.
The referee's report
If the claimed results hold, RASO makes a useful empirical contribution: it shows that large public skill corpora can be exploited cheaply throughout skill optimization without extra rollouts, and the component-wise evidence is reasonably strong. The paper's strengths include a clean RFSI-vs-RASI isolation (identical task/harness descriptions, procedure decomposition, and system prompt, differing only in the grounded lessons), fixed-initialization comparisons that separate the update contribution (Tables 4, 6-8), matched-or-fewer rollout counts (Table 10), explicit cost accounting (Table 9), and a concrete qualitative case of genuine cross-domain transfer from satellite-imagery code to a spreadsheet task (Fig. 5). The main reservations concern the unreleased and unmeasured corpus-exclusion control, the unstated split used for the K-selection analysis, and small margins on some benchmarks relative to three-seed standard errors; all are addressable within the manuscript's scope.
Pith's reading of the paper (a machine's summary, not the authors')
The paper's central claim is that agent skill optimization should draw on an external corpus of shared skills rather than relying only on the agent's own rollouts. It proposes RASO, whose retrieval-augmented initialization (RASI) builds a usable initial skill from task and harness descriptions without any environment rollouts, and whose retrieval-augmented update (RASU) retrieves external knowledge to patch observed failures during iterative refinement. The load-bearing mechanism is Cross-Harness Adaptation, which rewrites skills written for other domains and harnesses into the target harness's vocabulary because on SpreadsheetBench 92.9% of retrieved skills come from a mismatched harness. On four benchmarks and two models, RASO beats retrieval-free optimizers such as TextGrad, GEPA, SkillOpt, and WikiSkill while using equal or fewer rollouts, and the two stages contribute complementary gains. A reader should care because the result points to a cheaper skill-optimization recipe: mine the millions of already-shared skills instead of paying for rollout search.
What carries the argument. Cross-Harness Adaptation is the shared operation that carries the argument. Given a requirement (a task procedure in RASI, a textual gradient in RASU), the target task description, the target harness description, and the top-K retrieved skill sections, an adaptation agent produces a "lesson": a concise procedure re-expressed in the objects, commands, and units of the target harness. It applies three rules — strip domain-specific nouns and procedures without a counterpart in the target harness, focus exclusively on the requirement, and keep tool- or parameter-specific claims only when corroborated by the harness description — which is what converts retrieval from a mismatched source into usable guidance rather than contaminating the skill with inapplicable instructions.
Core claim. The central claim is that grounding both skill initialization and skill update in retrieved-and-adapted external knowledge yields higher agent task scores than optimizing solely from execution experience. On the paper's own terms, RASO "consistently outperforms baselines without retrieval-augmented skill initialization and updating," improving over the strongest competing method by up to +6.31 points on SpreadsheetBench with GPT-5.6-Luna and +11.30 on WebShop with Qwen-3.5-9B, while using exactly as many rollouts as TextGrad and WikiSkill and fewer than GEPA and SkillOpt. The paper further shows the gains are additive: on OfficeQA and SpreadsheetBench, RASI alone adds +5.23 and +6.78 points, RASU alone adds +6.86 and +9.40, while the combination reaches +8.33 and +11.66 over the fully retrieval-free baseline, and Cross-Harness Adaptation accounts for most of the RASI gain (+3.88 and +7.74). A qualitative trace attributes one gain to a retrieved satellite-imagery skill whose "skip empty groups" rule, once adapted, prevents an index shift in a spreadsheet task.
The premise it rests on. The result stands or falls on the per-benchmark blocklist that supposedly strips benchmark-specific skills from GitSkills before retrieval; because the blocklist is not released and residual leakage is not measured, the gains could come from retrieving target-solution content rather than from transferable cross-harness procedural knowledge.
If the paper is right (Pith's inferences, not the authors')
RASI produces a strong initial skill with zero rollouts, beating retrieval-free initialization and direct reuse (SkillRouter) on every benchmark and both backbones, so the first rollout budget can be spent on update rather than initialization.
The two stages are complementary: each independently improves on the fully retrieval-free baseline and the combination is best (+8.33 on OfficeQA, +11.66 on SpreadsheetBench), so neither stage subsumes the other.
RASU alone beats the strongest retrieval-free updater under the same RASI initialization (+1.94 over WikiSkill on OfficeQA, +3.09 over SkillOpt on SpreadsheetBench), showing the update-stage retrieval, not merely a better starting point, drives part of the gain.
Under matched budgets RASO is the cheapest method on three of four benchmarks and uses no more rollouts than the cheapest baselines, so the advantage is not bought with extra environment interaction.
Retrieval helps even from a tiny slice of the corpus: enabling retrieval from just 1% of GitSkills already improves on no-retrieval, and performance grows with corpus size.
If leakage is controlled, the result suggests a general recipe: any text corpus of procedural documents could replace GitSkills, so manuals, documentation, and web knowledge could be folded into skill optimization without additional rollouts.
Because RASI needs no rollouts, its main cost is the retrieval and adaptation calls themselves; the paper's cost table hints that retrieval-plus-adaptation can beat rollout search on price, but the full crossover point where a cheaper retrieval call should replace a rollout is left implicit.
The K=5 sweet spot for retrieved sections (gains up to 5, mild degradation at 10) suggests a stronger retriever than BM25, or a reranker, could extend the gains; the paper does not test that.
The qualitative example implies the value is in procedure-level structure (e.g., empty-group handling) rather than surface phrasing, which, if true, means the method should transfer to procedural documents that never mention an agent at all.
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
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.
The paper
Abstract
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbfRetrieval-Augmented Skill Optimization (RASO), a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbfRetrieval-Augmented Skill Initialization (RASI) constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbfRetrieval-Augmented Skill Update (RASU) iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
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 · 2026-09-30
The authors' main claim, as the classifier picked it out 1.00
“Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.08 · states limitation 0.06 · human participants 0.04 · controlled comparison 0.96 · randomized assignment 0.02 · states quantitative result 0.32 · compares with prior results 0.96 · mentions code or data availability 0.06
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.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. | background 1.00 | 0.09 | 0.02 | asserted 1.00 |
| Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. | gap 0.98 | 0.11 | 0.04 | asserted 1.00 |
| To address this, we propose \textbf{Retrieval-Augmented Skill Optimization (RASO)}, a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. | contribution 0.98 | 0.74 | 0.10 | asserted 0.98 |
| RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. | method 0.94 | 0.68 | 0.07 | asserted 0.98 |
| RASO comprises two complementary stages: \textbf{Retrieval-Augmented Skill Initialization (RASI)} constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbf{Retrieval-Augmented Skill Update (RASU)} iteratively refines the skill by retrieving external knowledge guided by execution feedback. | method 0.97 | 0.77 | 0.08 | asserted 0.98 |
| Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating. | result 1.00 | 0.96 | 0.87 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.99
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, 2026-09-30: 1 request, 5,756 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 (5)
Figures are the authors', reproduced from the paper.
References (18)
- [3] Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, and Zhongkai Hao. SE-GoS: Self-evolving graph-of-skills for skill library at scale.arXiv:2609.08228, on PithPith's reviewarXiv
- [4] Ryangkyung Kang, Hongcheol Cho, and Youngeun Kim. SkillRet: A large-scale benchmark for skill retrieval in LLM agents.arXiv:2605.05726, on PithPith's reviewarXiv
- [5] Fangzhou Li, Pagkratios Tagkopoulos, and Ilias Tagkopoulos. SkillFlow: Scalable and efficient agent skill retrieval system. InCOLM, 2026a. Hao Li, Chunjiang Mu, Jianhao Chen, Siyue Ren, Zhiyao Cui, Yiqun Zhang, Lei Bai, and Shuyue Hu. Organizing, orchestrating, and benchmarkin... on PitharXiv
- [7] Yongliang Miao, Ziyang Yu, Liang Zhao, Bowen Zhu, and Hasibul Haque. SkillLens: Adaptive multi-granularity skill reuse for cost-efficient LLM agents.arXiv:2605.08386, on PithPith's reviewarXiv
- [8] 10 Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation Jingwei Ni, Yihao Liu, Xinpeng Liu, Yutao Sun, Mengyu Zhou, Pengyu Cheng, Dexin Wang, Er- chao Zhao, Xiaoxi Jiang, and Guanjun Jiang. Trace2Skill: Distill trajectory-local lessons into transferable agent sk... on PithPith's reviewarXiv
- [9] URLhttps: //openai.com/index/gpt-5-6/. Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins, Ivan Zhou, Cindy Wang, Ashutosh Baheti, Owen Oertell, Jacob Portes, Sam Havens, Erich Elsen, Michael Bendersky, Matei Zaharia, and Xing Chen. OfficeQA Pro: An enterprise benchmark for end... on PitharXiv
- [10] Qianjun Pan, Yutao Yang, Junsong Li, Jie Zhou, Kai Chen, Xin Li, Qin Chen, and Liang He. Any- thing2Skill: Compiling external knowledge into reusable skills for agents.arXiv:2606.09316, on PithPith's reviewarXiv
- [12] Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, and Tu Vu. WikiSkill: Compiling agent experience into persistent knowledge for skill evolution. arXiv:2608.27454, on PithPith's reviewarXiv
- [13] Xiangru Tang, Tianrui Qin, Tianhao Peng, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, et al. Agent KB: Leveraging cross-domain experience for agentic problem solving.arXiv:2507.06229, on PitharXiv
- [14] Hanyu Wang, Yifan Lan, Bochuan Cao, Lu Lin, and Jinghui Chen. SkillGrad: Optimizing agent skills like gradient descent.arXiv:2605.27760, on PithPith's reviewarXiv
- [15] Tianle Xia, Lingxiang Hu, Yiding Sun, Ming Xu, Lan Xu, Siying Wang, Wei Xu, and Jie Jiang. GraSP: Graph-structured skill compositions for LLM agents.arXiv:2604.17870, on PithPith's reviewarXiv
- [16] 11 Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. Large language models as optimizers. InICLR, 2024a. John Yang, Carlos Jimenez, Alexander Wettig, Kilian Lieret, Sh... on PithPith's reviewarXiv
- [17] 12 Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation A APPENDIX A.1 IMPLEMENTATIONDETAILS For all update methods, we run skill optimization for 2 epochs overDtrain with a minibatch size of 40 tasks per iteration. For Qwen-3.5-9B, we use a sampling temperature... on Pith
- [18] Following SkillOpt (Yang et al., 2026), we use the same train/validation/test splits for all methods, so update acceptance and skill selection are per- formed on an identical validation set. OfficeQA.OfficeQA (Opsahl-Ong et al., on Pith
- [2021] Weihang Su, Jianming Long, Qingyao Ai, Qiaozhi He, Yichen Tang, Changyue Wang, Yiteng Tu, Yingbo Wang, and Yiqun Liu. Skill retrieval augmentation for agentic AI.arXiv:2604.24594, on PithPith's reviewarXiv
- [2024] Xiangcheng Meng, Shu Wang, and Yixiang Fang. SkillRAE: Agent skill-based context compilation for retrieval-augmented execution.arXiv:2605.10114, on PithPith's reviewarXiv
- [2025] URLhttps: //www.anthropic.com/engineering/equipping-agents-for-the-real-w orld-with-agent-skills. Kunfeng Chen, Qihuang Zhong, Juhua Liu, and Bo Du. SkillCAT: Contrastive, assessment- augmented and topology-aware skill self-evolution for LLM agents.arXiv:2606.13317, on PithPith's reviewarXiv
- [2026] Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu, and Marco Ortu. GitSkills: A dataset of agent skills on GitHub.arXiv:2608.10906, on PithPith's reviewarXiv
Cited by 1 Pith paper
Reviewed papers on Pith that cite this one. The full citation record
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.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment