- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes SkillRise, an end-to-end reinforcement learning framework for cross-task skill learning. A shared policy alternates between solving related tasks and updating an evolving skill document, with current-task rewards supervising task solving and discounted downstream rewards supervising skill curation.
Critical strengths
- The paper presents a clear and meaningful formulation for enabling agents to accumulate and reuse transferable skills across related but distinct tasks.
- SkillRise provides a simple and unified framework that uses a single policy for task solving and skill curation.
Critical weaknesses
- The related-work analysis is incomplete, making the novelty difficult to assess. Since the main contribution concerns transferable skill learning, the paper should position itself more carefully against the most relevant literature. SkillOS is only briefly discussed, while closely related works such as D2Skill, Skill1 are omitted. Without a detailed comparison of their problem settings, skill representations, training objectives, and transfer mechanisms, the paper’s contribution and technical advancement remain unclear.
- The baseline selection is not well aligned with the paper’s central claim. GiGPO and LaMer mainly represent general agentic RL or Meta-RL approaches, whereas the proposed method focuses on skill learning and transfer. The absence of strong skill-learning baselines weakens the main empirical comparison. Moreover, the reported results of 85.9% on ALFWorld and 84.4% on WebShop appear below recently reported state-of-the-art results, which further limits the evidence for the method’s competitiveness.
- The within-task adaptation experiment does not isolate the source of the reported generalization. Because most baselines do not explicitly learn or maintain transferable skills, the experiment cannot determine whether the improvement comes from the proposed cross-task skill-training mechanism or simply from having an explicit skill document. Comparisons with stronger skill-based methods or appropriate skill-memory controls are needed.
- The ablation study does not convincingly establish the importance of skill curation. The training curves of SkillRise and the no-curation variant are largely similar, with only a small difference that may plausibly result from random-seed variance. This result appears weaker than the paper’s claim that skill curation is central to the framework.
- The efficiency comparison may be unfair because RetroAgent and SkillRL are inherently multi-stage systems, whereas SkillRise contains only two main processes. The resulting runtime advantage is therefore largely expected, and the comparison excludes GiGPO and LaMer. A more informative evaluation would report both training time and success rate for all major baselines, for example in a performance-versus-compute scatter plot, to demonstrate whether SkillRise offers a genuine Pareto advantage.
Questions for authors
Please refer to the weakness