Artificial Intelligence · arXiv:2611.17007 v1 · submitted 12 Nov 2026 · 25 references
Skill Adapter: Personalized Modification and Online Routing of General-Purpose Skills
The paper says
“Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users.”
more of the abstract
In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. Agents must select currently applicable skills from an expanding skill pool and prepare candidates for subsequent steps. We propose Skill Adapter, which enables personalized modification and online routing of general-purpose skills. The system distills local adjustments from user requirements and execution feedback and stores them as Adapters linked to general-purpose skills. The routing agent selects general-purpose skills and applicable Adapters based on the current subtask, execution progress, and environmental feedback, incrementally maintaining a task-level online skill library that the main LLM reads on demand. The system preloads candidates for subsequent nodes and rechecks their applicability once actual inputs are determined. Reinforcement learning optimizes the two types of decisions using modification gains and routing outcomes, respectively. We evaluate Skill Adapter on ALFWorld, WebShop, and SkillsBench. Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks. Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 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 engineering paper on skill personalization and routing for LLM agents; the routing reward's reference set is underspecified, but the empirical gains are large and the ablation is thorough. This line is wrong
4 major objections · 8 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 25 references say.
The paper says, at §Reinforcement Learning, Eq. (14)
The review did not quote this passage.
Pith says: Objection 1 of 4 · major
The routing reward in Eq. (14) depends on a reference skill set S_gold_j, but the paper never describes how S_gold_j is constructed. This is a load-bearing issue: without a principled, reproducible definition, the routing policy's training signal is underspecified. If S_gold_j is derived from the same trajectories used to train the modification policy or from the same user feedback, the …
more of objection 1
… reward could be circular—rewarding the routing policy for selecting skills that match a set that was itself inferred from the policy's own prior selections. If S_gold_j requires human annotation, the method's scalability and reproducibility are limited. The authors must specify the provenance of S_gold_j, how it is obtained for each task node during training, and whether it can be constructed without human involvement. This is the weakest assumption identified by the reader, and it is indeed load-bearing.
The paper says, at §Experiments, Table 3
The review did not quote this passage.
Pith says: Objection 2 of 4 · major
The ablation study (Table 3) shows that adding the routing policy alone yields a mean success rate of 65.28%, while the full method (both policies) yields 71.86%. However, the routing policy reward (Eq. 14) uses S_gold_j, which is not defined.
more of objection 2
If S_gold_j is constructed using the modification policy's outputs or the same trajectories, then the routing policy's training is not independent, and the ablation comparison may conflate effects. The authors should clarify whether S_gold_j is held fixed during routing policy training and how it is obtained independently of the modification policy.
The paper says, at §Method, Personalized Modification
The review did not quote this passage.
Pith says: Objection 3 of 4 · major
The modification policy is trained using a reward based on change in task success rate on a held-out task set Q_evalu (Eq. 12). The paper states that 'the general-purpose skill pool, user conditions, executor, and routing configuration are kept identical before and after modification' (sentence b105).
more of objection 3
However, it is not clear whether the routing policy is also kept fixed during modification policy training. If the routing policy is updated concurrently or if the routing configuration changes, the reward signal may be confounded. The authors should specify whether the routing policy is frozen during modification training and vice versa.
The paper says, at §Experiments, Main Results
The review did not quote this passage.
Pith says: Objection 4 of 4 · major
The paper reports that Skill Adapter reduces mean execution time compared to SkillRL on all three benchmarks. However, execution time includes skill retrieval, modification and routing inference, main-LLM inference, and environment interaction. The routing agent preloads candidates for subsequent nodes, which could increase inference time per step but reduce total steps.
more of objection 4
The paper should provide a breakdown of execution time to show where the savings come from. Without this, it is unclear whether the time reduction is due to better skill selection (fewer steps) or more efficient inference.
8 minor objections
The paper says, at §Abstract
Pith says: minor objection 1 of 8
The abstract states 'Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills.' This is a strong claim, but the scaling experiment (Figure 3, left) only shows results up to 1,000 skills. The paper should clarify whether the advantage holds at larger scales or if there is a trend of diminishing returns.
The paper says, at §Method, Eq. (4)
Pith says: minor objection 2 of 8
The notation for Adapter definition uses 'esu,i,k' but the tilde may not render clearly in all formats. Consider using a different notation or clarifying in text.
show 6 more
The paper says, at §Experiments, Table 1
Pith says: minor objection 3 of 8
The table caption says 'Higher success rates and scores are better; lower mean execution times are better.' This is clear, but the table includes both success rate and score for WebShop. The score is defined in the text but not in the caption; consider adding a brief definition or reference.
The paper says, at §Related Work
Pith says: minor objection 4 of 8
The related work section is well-structured but could benefit from a brief comparison of Skill Adapter's approach to skill modification versus existing methods like Voyager or ExpeL. Currently, it only states that Skill Adapter 'distills historical execution experience into general-purpose skills and uses associated Adapters to express local modifications.' A more explicit contrast would help position the contribution.
The paper says, at §Method, Online Routing
Pith says: minor objection 5 of 8
The description of candidate retrieval (Eq. 6) mentions 'topic-based search and semantic matching' and 'candidate expansion along skill composition relations.' The paper should provide more detail on how topics are defined and how composition relations are extracted from trajectories. This is important for reproducibility.
The paper says, at §Experiments, Ablation Study
Pith says: minor objection 6 of 8
Table 3 shows the effect of adding components incrementally. However, the 'Skills' row includes both 'Trajectory pool only' and 'Skills + General-purpose skill pool.' The baseline 'Skills' is not clearly defined; it seems to refer to using only trajectory-level skills without general-purpose skills. Clarify what 'Skills' means in this context.
The paper says, at §Conclusion
Pith says: minor objection 7 of 8
The conclusion restates the contributions and results but does not discuss limitations or future work. Adding a limitations paragraph would strengthen the paper and provide direction for follow-up research.
The paper says, at General
Pith says: minor objection 8 of 8
The paper uses the term 'Adapter' which is also used in the parameter-efficient fine-tuning literature (e.g., LoRA adapters). While the meaning is different, the authors should acknowledge this potential confusion and clarify that their Adapters are not the same as LoRA-style adapters.
What would settle it
Publish the construction procedure for S_gold_j for each task node in each benchmark, including whether it is derived from human annotation, from the training trajectories, or from an independent oracle. Then re-run the routing policy training with S_gold_j held fixed and independently verifiable (e.g., from a separate held-out set of expert demonstrations). If the routing reward's F1 score no longer correlates with task success, or if the performance gain over SkillRL shrinks substantially, the current reward formulation is not robust.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic agrees
- Editor wrote the verdict above
- Referee major revision: 4 major objections, 8 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
This is a solid engineering paper on personalizing general-purpose skills for LLM agents. The core idea—storing user-specific modifications as Adapters linked to shared skills and routing them online during task execution—is well motivated and the implementation is clean. The empirical results are strong: 8–17 percentage point gains over SkillRL across three benchmarks, with reduced execution time. The ablation study is thorough and shows that each component (skill pool, routing organization, DAG preloading, RL for each policy) contributes. The scaling experiment to 1,000 skills, while showing a 15% relative drop for Skill Adapter, still maintains a 20-point lead over SkillRL, which is credible.
The main soft spot is the routing reward (Equation 14). It uses a reference skill set S_gold_j to compute an F1 score for successful task executions, but the paper never says how S_gold_j is obtained. If it comes from the same trajectories used to train the modification policy, the reward could be circular. If it requires human annotation, the method's scalability is limited. The authors do not acknowledge this gap. This is a load-bearing issue because the routing policy's training signal depends on it. The paper also does not release code or data, which limits reproducibility, though this is common for agent papers at this stage. The scaling experiment's drop is not discussed, which is a minor omission.
Who this is for: researchers working on skill-based LLM agents, especially those interested in personalization and online routing. The paper is clearly written and the method is reproducible in principle. It deserves a serious referee, but the referee should press on S_gold_j's provenance and on the scaling drop.
Recommendation: accept after major revision, conditional on clarifying how S_gold_j is constructed and discussing the scaling drop. The core contribution is real and the experiments are otherwise solid.
The strongest objection
The routing reward (Equation 14) uses a reference skill set S_gold_j to compute an F1 score for successful task executions. The paper never specifies how S_gold_j is obtained. If S_gold_j is derived from the same trajectories used to train the modification policy, the reward could be circular: the routing policy is rewarded for selecting skills that match a set that was itself inferred from the policy's own prior selections. If S_gold_j requires human annotation, the method's scalability and reproducibility are limited. The paper's own text (sentence b105) states that 'the general-purpose skill pool, user conditions, executor, and routing configuration are kept identical before and after modification' for the modification reward, but no analogous statement or construction procedure is given for S_gold_j. This is the weakest assumption identified by the reader, and it is indeed load-bearing: without a principled, reproducible way to define S_gold_j, the routing reward is underspecified and the reported routing improvements cannot be independently verified or attributed to the proposed mechanism rather than to an arbitrary or circular reference set.
The reader's weakest_assumption correctly identifies the missing specification of S_gold_j as the most critical unresolved issue. The paper's central claim—that Skill Adapter improves success rates by 11.43 percentage points on average—depends on the routing policy being trained with a meaningful reward. If S_gold_j is arbitrary or circular, the routing policy's learned behavior may not generalize or may be an artifact of the training data. The paper does not acknowledge this limitation; no sentence in the 'Limitations the authors state' category was found. The concern is concrete and testable: the authors can specify how S_gold_j is constructed and verify that the reward is not circular. Other concerns (missing code, scaling drop, ablation design) are secondary or partially addressed by the paper's own data. The verdict should remain CONDITIONAL because the paper's empirical results are otherwise well-presented and the method is clearly motivated; the condition is that the S_gold_j construction must be clarified and shown to be non-circular. Agreement with the reader is 'agree' because the reader's weakest_assumption matches this concern exactly.
The referee's report
If the results hold, Skill Adapter addresses a practical challenge: adapting general-purpose skills to individual user needs and dynamically selecting them during long-horizon tasks. The idea of separating shared skill procedures from user-specific modifications via Adapters is sensible and could be useful for deploying LLM agents in personalized settings. The empirical gains are substantial, and the scaling experiment with 1,000 skills suggests robustness. However, the significance is tempered by the underspecification of the reference skill set S_gold_j used in the routing reward, which is critical for reproducibility and for ruling out circularity.
Pith's reading of the paper (a machine's summary, not the authors')
Large language model (LLM) agents often reuse skills, which are step-by-step procedures for tasks like translating a document or browsing a website. However, different users have different needs: one person might want to preserve the original layout of a translated contract, while another only cares about the text. Skill Adapter stores these personal preferences as small modifications called Adapters, which are attached to general-purpose skills. During a task, a routing agent picks the right skill and Adapter for each step, updating its choices as the task progresses and new information arrives. The system uses reinforcement learning to improve both the personalization and the routing decisions over time. In experiments on three benchmarks, Skill Adapter outperformed existing methods, including SkillRL, by 8 to 17 percentage points in success rate while also reducing execution time. The advantage held even when the pool of skills grew to 1,000 items.
Core claim. Skill Adapter improves task success rates by an average of 11.43 percentage points over SkillRL across ALFWorld, WebShop, and SkillsBench, and reduces mean execution time on all three benchmarks (Table 1, Table 2, sentence b11).
The premise it rests on. The reward for the routing policy (Equation 14) depends on a reference skill set S_gold_j, which is assumed to be available for each task node during training. The paper does not specify how S_gold_j is constructed or whether it can be obtained without human annotation. If S_gold_j is derived from the same trajectories used to train the modification policy, this could introduce circularity in the routing reward.
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
Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users. In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. Agents must select currently applicable skills from an expanding skill pool and prepare candidates for subsequent steps. We propose Skill Adapter, which enables personalized modification and online routing of general-purpose skills. The system distills local adjustments from user requirements and execution feedback and stores them as Adapters linked to general-purpose skills. The routing agent selects general-purpose skills and applicable Adapters based on the current subtask, execution progress, and environmental feedback, incrementally maintaining a task-level online skill library that the main LLM reads on demand. The system preloads candidates for subsequent nodes and rechecks their applicability once actual inputs are determined. Reinforcement learning optimizes the two types of decisions using modification gains and routing outcomes, respectively. We evaluate Skill Adapter on ALFWorld, WebShop, and SkillsBench. Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks. Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills.
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 · 2026-11-13
The authors' main claim, as the classifier picked it out 0.97
“Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.10 · human participants 0.08 · controlled comparison 0.90 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.98 · mentions code or data availability 0.03
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 |
|---|---|---|---|---|
| Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users. | background 0.94 | 0.09 | 0.02 | asserted 1.00 |
| In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. | background 0.98 | 0.07 | 0.01 | asserted 1.00 |
| Agents must select currently applicable skills from an expanding skill pool and prepare candidates for subsequent steps. | background 0.90 | 0.06 | 0.02 | asserted 1.00 |
| We propose Skill Adapter, which enables personalized modification and online routing of general-purpose skills. | contribution 1.00 | 0.82 | 0.16 | asserted 1.00 |
| The system distills local adjustments from user requirements and execution feedback and stores them as Adapters linked to general-purpose skills. | method 0.97 | 0.83 | 0.05 | asserted 1.00 |
| The routing agent selects general-purpose skills and applicable Adapters based on the current subtask, execution progress, and environmental feedback, incrementally maintaining a task-level online skill library that the main LLM reads on demand. | method 0.99 | 0.79 | 0.09 | asserted 1.00 |
| The system preloads candidates for subsequent nodes and rechecks their applicability once actual inputs are determined. | method 0.99 | 0.73 | 0.03 | asserted 1.00 |
| Reinforcement learning optimizes the two types of decisions using modification gains and routing outcomes, respectively. | method 0.99 | 0.85 | 0.05 | asserted 1.00 |
| We evaluate Skill Adapter on ALFWorld, WebShop, and SkillsBench. | method 0.78 | 0.95 | 0.03 | asserted 0.96 |
| Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks. | result 1.00 | 0.95 | 0.46 | asserted 1.00 |
| Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills. | result 0.99 | 0.94 | 0.17 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.94
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, 2026-11-13: 1 request, 8,699 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 (3)
Figures are the authors', reproduced from the paper.
References (25)
- [4] SkillNet: Create, Evaluate, and Connect AI Skills. arXiv:2603.04448. Liu, X.; Yu, H.; Zhang, H.; Xu, Y.; Lei, X.; Lai, H.; Gu, Y.; Ding, H.; Men, K.; Yang, K.; et al on PithPith's reviewarXiv
- [5] AgentBench: Evaluating LLMs as Agents. arXiv:2308.03688. Liu, Y.; Ji, J.; An, L.; Jaakkola, T.; Zhang, Y.; and Chang, S on PithPith's reviewarXiv
- [6] How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings. arXiv:2604.04323. Lu, Y.; Yu, H.; and Khashabi, D on PithPith's reviewarXiv
- [7] GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution. arXiv:2307.08775. OpenAI on PithPith's reviewarXiv
- [8] MemGPT: Towards LLMs as Operating Systems. arXiv:2310.08560. Paranjape, B.; Lundberg, S.; Singh, S.; Hajishirzi, H.; Zettle- moyer, L.; and Ribeiro, M. T on PithPith's reviewarXiv
- [9] ART: Automatic Multi- step Reasoning and Tool-use for Large Language Models. arXiv:2303.09014. Park, J. S.; O’Brien, J. C.; Cai, C. J.; Morris, M. R.; Liang, P.;andBernstein,M.S.2023. GenerativeAgents: Interactive Simulacra of Human Behavior. InProceedings of the 36th Annual A... on PithPith's reviewarXiv
- [10] Gorilla: Large Language Model Connected with Massive APIs. arXiv:2305.15334. Qian, C.; Han, C.; Fung, Y. R.; Qin, Y.; Liu, Z.; and Ji, H on PithPith's reviewarXiv
- [11] CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models. arXiv:2305.14318. Qin, Y.; Liang, S.; Ye, Y.; Zhu, K.; Yan, L.; Lu, Y.; Lin, Y.; Cong, X.; Tang, X.; Qian, B.; et al on PithPith's reviewarXiv
- [12] ToolLLM: Facilitating Large Language Models to Master 16000+ Real- world APIs. arXiv:2307.16789. Robertson, S.; and Zaragoza, H on PithPith's reviewarXiv
- [13] Toolformer: LanguageModelsCanTeachThemselvestoUse Tools. arXiv:2302.04761. Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; and Klimov, O on PithPith's reviewarXiv
- [16] Dynamic SkillLifecycleManagementforAgenticReinforcementLearn- ing. arXiv:2605.10923. Shinn, N.; Cassano, F.; Berman, E.; Gopinath, A.; Narasimhan, K.; and Yao, S on PithPith's reviewarXiv
- [17] Dynamic Dual-Granularity Skill Bank for Agentic RL. arXiv:2603.28716. Wang, G.; Xie, Y.; Jiang, Y.; Mandlekar, A.; Xiao, C.; Zhu, Y.; Fan, L.; and Anandkumar, A on PithPith's reviewarXiv
- [18] Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv:2305.16291. Wang, J.; Yan, Q.; Wang, Y.; Tian, Y.; Mishra, S. S.; Xu, Z.; Gandhi, M.; Xu, P.; and Cheong, L. L on PithPith's reviewarXiv
- [20] AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155. Xia, P.; Chen, J.; Wang, H.; Liu, J.; Zeng, K.; Wang, Y.; Han, S.; etal on PithPith's reviewarXiv
- [21] SkillRL:EvolvingAgentsviaRecursiveSkill- Augmented Reinforcement Learning. arXiv:2602.08234. Xie, T.; Zhang, D.; Chen, J.; Li, X.; Zhao, S.; Cao, R.; Hua, T. J.; Cheng, Z.; Shin, D.; Lei, F.; Liu, Y.; Xu, Y.; Zhou, S.; Savarese,S.;Xiong,C.;Zhong,V.;andYu,T.2024. OSWorld: Bench... on PithPith's reviewarXiv
- [22] Qwen3 Technical Report. arXiv:2505.09388. Yang, J.; Jimenez, C. E.; Wettig, A.; Lieret, K.; Yao, S.; Narasimhan, K.; and Press, O on PithPith's reviewarXiv
- [23] SWE-agent: Agent- Computer Interfaces Enable Automated Software Engineer- ing. arXiv:2405.15793. Yao, S.; Chen, H.; Yang, J.; and Narasimhan, K on PithPith's reviewarXiv
- [24] ExpeL: LLM Agents Are Experiential Learners. arXiv:2308.10144. Zheng, Y.; Zhang, Z.; Ma, C.; Yu, Y.; Zhu, J.; Dong, B.; and Zhu, H on PithPith's reviewarXiv
- [25] SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale. arXiv:2603.22455. Zhou, S.; Xu, F. F.; Zhu, H.; Zhou, X.; Lo, R.; Sridhar, A.; Cheng, X.; Ou, T.; Bisk, Y.; Fried, D.; Alon, U.; and Neubig, G on PithPith's reviewarXiv
- [2017] Proximal Policy Optimization Algorithms. arXiv:1707.06347. Shao, Z.; Wang, P.; Zhu, Q.; Xu, R.; Song, J.; Bi, X.; Zhang, H.; et al on PithPith's reviewarXiv
show 5 more
- [2022] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv:2204.01691. Bai, T.; Wan, Z.; Zhou, P.; Yu, X.; Zhao, W.; You, Y.; and Tsang, I. W on PithPith's reviewarXiv
- [2023] Mind2Web: Towards a Generalist Agent for the Web. arXiv:2306.06070. Li, D.; Li, Z.; Du, H.; Wu, X.; Gui, S.; Kuang, Y.; and Sun, L. 2026a. Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills. arXiv:2604.05333. Li, X.; Chen, W.; Liu, Y.; Zheng, S.; C... on PithPith's reviewarXiv
- [2024] DeepSeekMath: Pushing the Lim- its of Mathematical Reasoning in Open Language Models. arXiv:2402.03300. Shen, J.; Zhang, T.; Zhao, X.; and Cheng, H on PithPith's reviewarXiv
- [2025] Reinforce- ment Learning for Self-Improving Agent with Skill Library. arXiv:2512.17102. Wu, Q.; Bansal, G.; Zhang, J.; Wu, Y.; Li, B.; Zhu, E.; Jiang, L.; Zhang, X.; Zhang, S.; Liu, J.; Awadallah, A. H.; White, R. W.; Burger, D.; and Wang, C on PithPith's reviewarXiv
- [2026] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale. arXiv:2606.03056. Deng, X.; Gu, Y.; Zheng, B.; Chen, S.; Stevens, S.; Wang, B.; Sun, H.; and Su, Y on PithPith's reviewarXiv
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