Reviewer #1
Questions
2. I am an expert on the topic of the paper.
Disagree
3. The title and abstract reflect the content of the paper.
Agree
4. The paper discusses, cites and compares with all relevant related work
Agree
5. Please justify the previous choice (Required if “Strongly Disagree” or “Disagree” is chosen, otherwise write "n/a")
n/a
6. Readability and paper organization: The writing and language are clear and structured in a logical manner.
Agree
7. The paper adheres to ISMIR 2026 submission guidelines (uses the ISMIR 2026 template, has at most 6 pages of technical content followed by “n” pages of references, AI usage declaration or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.
Yes
8. Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.
Agree
9. Scholarly/scientific quality: The content is scientifically correct.
Agree
10. Please justify the previous choice (Required if "Strongly Disagree" or "Disagree" is chosen, otherwise write "n/a")
n/a
11. Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.
Agree
12. The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.
Agree
13. Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.
Disagree (Standard topic, task, or application)
14. Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.
Agree
15. Please explain your assessment of reusable insights in the paper.
The core idea that domain knowledge for music reasoning can be represented not only as static textbook content, but also as structured procedural skills that can be retrieved and injected into pretrained LLMs at inference time. While the paper focuses on symbolic music understanding, this perspective may also be useful for other MIR tasks that require explicit, step-by-step domain reasoning.
16. AI Usage Policy: The paper complies with the ISMIR 2026 AI Usage Policy for Authors. (Authors are welcome to use any tool they wish for preparing and writing the paper but they must ensure that all content is correct and original. Authors must declare any use of LLMs and AI tools if it's a part of core methodology (including literature review, related work, generated figures, tables or other illustrations). Using AI tools for editing purposes (e.g,. checking grammar and fixing typos) need not be declared. Please pay attention to any hallucinated text, figures, or references and flag them in the comments below)
Agree
17. Please justify the previous choice (Required if "Disagree" is chosen, otherwise write "n/a")
n/a
18. Write ONE line (in your own words) with the main take-home message from the paper.
The paper proposes SYMSKILL, a skill-augmented framework derived from music-theory curricula that provides structured music-theory procedures to guide tool-free LLM reasoning for symbolic music question answering.
21. Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.
Agree
22. Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines
Weak accept
23. Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.
The paper proposes SYMSKILL, which attempts to convert music-theory curricula into structured procedural skills that can guide LLMs in symbolic music reasoning. It seems a relevant and potentially useful direction, especially for tool-free reasoning with relatively small LLMs. My main concerns lie in the choice of baselines and the analysis of some experimental results.

The paper positions SYMSKILL against both prompt-based and tool-augmented approaches, but the experiments only compare it against tool-free baselines. The benefits SYMSKILL provides over tool-augmented approaches are therefore not clear.

On the other hand, I view SYMSKILL as a inference-time structured domain-knowledge injection method, which makes me wonder how does it compare to other methods in the same family. The "memory" baseline in the paper is one relevant approach, as it resembles RAG, but I wondering whether more approaches should be compared with or at least discussed.

Regarding the experimental results, I'd appreciate a more in-depth discussion. For example in Table 2, the memory baseline consistently outperforms other approaches on CTHA, why is that? why skill graph not helpful for tonal-harmonic analysis? And in Table 4, the memory baseline performs extremely poorly across the board. Even though it is expectable that music theory context might not be directly helpful for symbolic score manipulation and recognition, the performance drop is still surprising, and I would appreciate more discussion on this.

Overall, the proposed approach seems promising, but it would benefit from comparing with more complete set of baselines and a more in-depth discussion of the experimental results.



Reviewer #2
Questions
2. I am an expert on the topic of the paper.
Disagree
3. The title and abstract reflect the content of the paper.
Strongly agree
4. The paper discusses, cites and compares with all relevant related work
Agree
5. Please justify the previous choice (Required if “Strongly Disagree” or “Disagree” is chosen, otherwise write "n/a")
n/a
6. Readability and paper organization: The writing and language are clear and structured in a logical manner.
Agree
7. The paper adheres to ISMIR 2026 submission guidelines (uses the ISMIR 2026 template, has at most 6 pages of technical content followed by “n” pages of references, AI usage declaration or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.
Yes
8. Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.
Strongly agree
9. Scholarly/scientific quality: The content is scientifically correct.
Disagree
10. Please justify the previous choice (Required if "Strongly Disagree" or "Disagree" is chosen, otherwise write "n/a")
It is in between disagree and agree range.
1. The author should maintain consistent variables. If query is denoted as q in subsection 4.1, the same notation should be used in section 5 instead of x (e.g. τq = ΦΩ(q) / hx = ΦΩ(x) ).
2. The authors should provide definitions for each parameter.
What are r_ij, Γ_i, E_i in graph update (in Equation 4)
3. The graph update operation appears to only add information. If the operation also involves modifications, such as removing ambiguity, this should be explicitly mentioned. If there are no modification or deletion operations, the term ‘update’ needs to be reconsidered.
4. Requires clarification of several details. I will comment on them in Question 23.
11. Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.
Agree
12. The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.
Agree
13. Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.
Agree (Novel topic, task, or application)
14. Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.
Agree
15. Please explain your assessment of reusable insights in the paper.
The paper provides references for the LLM model and the three datasets: CSyMR, MusicTheoryBench, and SSMR-Bench.
The codebase for two-layer critic is provided.
16. AI Usage Policy: The paper complies with the ISMIR 2026 AI Usage Policy for Authors. (Authors are welcome to use any tool they wish for preparing and writing the paper but they must ensure that all content is correct and original. Authors must declare any use of LLMs and AI tools if it's a part of core methodology (including literature review, related work, generated figures, tables or other illustrations). Using AI tools for editing purposes (e.g,. checking grammar and fixing typos) need not be declared. Please pay attention to any hallucinated text, figures, or references and flag them in the comments below)
Agree
17. Please justify the previous choice (Required if "Disagree" is chosen, otherwise write "n/a")
n/a
18. Write ONE line (in your own words) with the main take-home message from the paper.
This paper proposes a two-stage framework for symbolic music reasoning: constructing a Skill Graph through symbolic music skill ontology projection and jointly comparing successful and failed self-exam episodes.
21. Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.
Disagree
22. Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines
Weak accept
23. Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.
[Organization]
- For organization, grouping 4 and 5 as Methodology looks clear.

[Methodology]
- Overall, there are overloading notations and undefined variables.
- Include that symbolic music skill s = (Os, Ts, ℓs, ds, Ps, Is, As, Ys) is a element of V (s ∈ V)
- In 3.2, are edges empty set during initialization?
- In symbolic music skill definition, l_s and d_s are separate components. But in Table 1, d (strand) seems to be a subtype of l (scale). Could you clarify the relationship between these two components?
- In Section 4.2, the session bundle is processed jointly. However, the number of accepted and rejected episodes may differ. How pairs are constructed when the two sets have different sizes?

[Experiments]
- Missing baseline comparison: The related work includes the CharMusician [11] paper, which reports zero-shot accuracy on MusicTheoryBench. Since Table 3 reports the accuracy of the proposed model, a baseline comparison should also be included, at least for the overall ‘All’ category.

[Grammar]
Line 16, Line 155: organized
Line 158: localize
Line 169: extracted
Line 191: distills
Figure 3 (2): In the bundle’s failed episode, the analyst selects …
Figure 3 (3): generalizes
Figure 3 (L5): via specialization/conflict
Line 261: neighbors
Reviewer #3
Questions
2. I am an expert on the topic of the paper.
Agree
3. The title and abstract reflect the content of the paper.
Agree
4. The paper discusses, cites and compares with all relevant related work
Agree
5. Please justify the previous choice (Required if “Strongly Disagree” or “Disagree” is chosen, otherwise write "n/a")
n/a
6. Readability and paper organization: The writing and language are clear and structured in a logical manner.
Agree
7. The paper adheres to ISMIR 2026 submission guidelines (uses the ISMIR 2026 template, has at most 6 pages of technical content followed by “n” pages of references, AI usage declaration or ethical considerations, references are well formatted). If you selected “No”, please explain the issue in your comments.
Yes
8. Relevance of the topic to ISMIR: The topic of the paper is relevant to the ISMIR community. Note that submissions of novel music-related topics, tasks, and applications are highly encouraged. If you think that the paper has merit but does not exactly match the topics of ISMIR, please do not simply reject the paper but instead communicate this to the Program Committee Chairs. Please do not penalize the paper when the proposed method can also be applied to non-music domains if it is shown to be useful in music domains.
Agree
9. Scholarly/scientific quality: The content is scientifically correct.
Agree
10. Please justify the previous choice (Required if "Strongly Disagree" or "Disagree" is chosen, otherwise write "n/a")
n/a
11. Novelty of the paper: The paper provides novel methods, applications, findings or results. Please do not narrowly view "novelty" as only new methods or theories. Papers proposing novel musical applications of existing methods from other research fields are considered novel at ISMIR conferences.
disagree
12. The paper provides all the necessary details or material to reproduce the results described in the paper. Keep in mind that ISMIR respects the diversity of academic disciplines, backgrounds, and approaches. Although ISMIR has a tradition of publishing open datasets and open-source projects to enhance the scientific reproducibility, ISMIR accepts submissions using proprietary datasets and implementations that are not sharable. Please do not simply reject the paper when proprietary datasets or implementations are used.
Agree
13. Pioneering proposals: This paper proposes a novel topic, task or application. Since this is intended to encourage brave new ideas and challenges, papers rated "Strongly Agree" and "Agree" can be highlighted, but please do not penalize papers rated "Disagree" or "Strongly Disagree". Keep in mind that it is often difficult to provide baseline comparisons for novel topics, tasks, or applications. If you think that the novelty is high but the evaluation is weak, please do not simply reject the paper but carefully assess the value of the paper for the community.
Disagree (Standard topic, task, or application)
14. Reusable insights: The paper provides reusable insights (i.e. the capacity to gain an accurate and deep understanding). Such insights may go beyond the scope of the paper, domain or application, in order to build up consistent knowledge across the MIR community.
Disagree
15. Please explain your assessment of reusable insights in the paper.
The idea of turning textbook chapters into a graph-based reasoning roadmap for LLMs
16. AI Usage Policy: The paper complies with the ISMIR 2026 AI Usage Policy for Authors. (Authors are welcome to use any tool they wish for preparing and writing the paper but they must ensure that all content is correct and original. Authors must declare any use of LLMs and AI tools if it's a part of core methodology (including literature review, related work, generated figures, tables or other illustrations). Using AI tools for editing purposes (e.g,. checking grammar and fixing typos) need not be declared. Please pay attention to any hallucinated text, figures, or references and flag them in the comments below)
Agree
17. Please justify the previous choice (Required if "Disagree" is chosen, otherwise write "n/a")
n/a
18. Write ONE line (in your own words) with the main take-home message from the paper.
The paper proposes extracting step-by-step analytical routines from music theory texts into a reusable skill graph.
21. Potential to generate discourse: The paper will generate discourse at the ISMIR conference or have a large influence/impact on the future of the ISMIR community.
Disagree
22. Overall evaluation: Keep in mind that minor flaws can be corrected, and should not be a reason to reject a paper. Please familiarize yourself with the reviewer guidelines at https://ismir.net/reviewer-guidelines
Weak reject
23. Main review and comments for the authors. Please summarize strengths and weaknesses of the paper. It is essential that you justify the reason for the overall evaluation score in detail. Keep in mind that belittling or sarcastic comments are not appropriate.
This paper introduces SYMSKILL, a framework that extracts structured analytical workflows from music theory textbooks to build a "skill graph."

Limitations: The inference evaluation is entirely restricted to Qwen3.5-4B and 9B.
Without testing larger architectures, it is difficult to tell if SYMSKILL actually is state-of-the-art in MIR or just acts as supports smaller models.