-
For the explanation mechanism(183-193), the authors exchange complete explanation collections. So there can be changes in wording, length, source links and restated facts together, right? The 13.48 point improvement is nice to see but I am not sure which of these factors is actually responsible for the gain. Also it is very difficult to connect this result directly to the original 18.36 point improvement from source sharing since the two experiments use different interventions.
-
I don't think the preservation note used as the main baseline may be neutral. In Table 3, acc decreases from 74.61% to 70.12% without sharing. So the reported 27.34 point improvement over preservation may partly reflect a harmful baseline rather than only the benefit of the resolved revision. IMO it would be useful to test alternative neutral or length-matched notes to separate the effect of adding a revision from the effect of providing the correct judgment.
-
Here the main motivation is that upstream information sharing helps the final model use evidence more effectively through better report formation. But if I look at the source only comparisons, I see a very different picture. For example, in the historical HiddenBench regenerated-report setting(Appendix D.5), source-only accuracy reaches 87.69% but the full-report condition achieves only 45.38% even after supporting-material exchange. Well this large performance gap actually raises a fundamental question: if reports help the model use evidence more effectively, why does adding reports lead to such a substantial drop in acc? I understand these are different experimental settings and the authors also acknowledge this limitation. But the paper does not sufficiently explain the difference. This matters a lot because your main experiments show that sharing improves performance within a report-based workflow but do not establish that using reports is better than directly providing the original sources. I think this issue deserves more analysis rather than being left mainly as a limitation.
-
The main experiments rely on synthetic tasks and the benchmark evaluations use different controls so generalizability is still a concern. Also the revision experiment(Sec. 5.1) relies on ground-truth corrections rather than agent-generated ones.
-
The introduction cites only three works. This makes me feel that the authors have not sufficiently reviewed the existing literature which also makes it harder to understand the novelty and positioning of the paper. For instance, [1,2,3] are very relevant to the questions studied here. Authors should include more relevant references throughout the paper to better support their claims and connect their findings to existing literature.
I am leaning toward weak rejection since the main mechanism is still unclear to me and the practical benefits need stronger evidence. Hopefully, the authors can clear up these concerns during the rebuttal.
[1] https://arxiv.org/pdf/2508.17536
[2] https://arxiv.org/pdf/2512.08296
[3] Liu et al. "Lost in the middle: How language models use long contexts." TACL, 2024.