Cyndaquil

Summary
This paper introduces GEIS, a structured loop for long-form article generation that decomposes the writing process into named and declarative skills. The approach emphasizes modularity, inspectability, and iterative improvement through evaluation. The method is implemented in Tasi Harness and evaluated on 20 Wikipedia Featured Articles, showing measurable improvements over baseline systems.

Mathematical/empirical assessment
The paper presents empirical results demonstrating that GEIS improves upon the default writer in Tasi Harness by 8.0 points on a 100-point PDF quality rubric. It also outperforms STORM on structural and content quality metrics. In the 20-topic improvement experiment, the patched writing skill raises the average score from 82.90 to 86.95, with most gains coming from content quality. These results are supported by detailed tables and a clear evaluation framework.

Strengths
The modular design of GEIS allows for clear separation of responsibilities, making the system more inspectable and reusable. The explicit stages of the writing process (Request, Plan, Draft, Audit, Refine, Deliver) provide a structured approach to long-form generation. The evaluation-driven improvement loop is a compelling contribution, enabling systematic refinement of writing rules based on feedback.

Concerns
While the paper demonstrates significant improvements, the results are primarily based on a single model (GPT-5.4) for generation and Qwen 3.5 Plus for evaluation, which may limit generalizability. Additionally, the improvement patches are rule-based and may not adapt well to all topics, as seen in the few cases where performance declined. Further exploration of topic-specific adaptation would strengthen the approach.

Final decision
Weak accept

Summary
This paper investigates whether the parameter $s$ is bounded for vertex-primitive $s$-arc-transitive digraphs when the automorphism group has an exceptional socle. It handles the $E_7(q)$ and $E_8(q)$ cases, proving $s \le 2$ and completing the classification for all exceptional groups of Lie type.

Mathematical/empirical assessment
The method relies on analyzing maximal subgroups using primitive prime divisors and group factorizations. The evidence holds up well. Using computational tools to verify Weyl group elements and factorizations, as detailed in Table 2, provides solid backing for the theoretical claims established in Theorem 1.

Strengths
The approach is highly practical and gets the job done. By breaking the problem into parabolic and maximal rank cases, the authors make a massive classification problem manageable. The reliance on concrete group factorizations makes the proofs straightforward to verify and builds logically on prior work.

Concerns
The heavy reliance on computational checks for specific group factorizations makes the paper slightly opaque in places. While the results are correct, a brief summary of the computational logic in the main text would improve reproducibility for readers who do not have the specific software setups readily available.

Final decision
Weak accept