- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes DAC, an RL framework that decomposes agentic search into a searcher and a generator sharing one model. During training, the generator may abstain when evidence seems insufficient. Its decision enters the searcher's reward, so the searcher is rewarded only for evidence that is externally sufficient and accepted by generator. The generator is rewarded for correct answers on sufficient evidence or abstention on insufficient evidence. Hard-positive augmentation adds distractor documents to sufficient evidence to prevent over-abstention, and turn-level difference rewards densify the searcher signal. On seven QA benchmarks with Qwen2.5-7B-Instruct and Qwen3-8B, DAC improves average EM over the strongest baselines by 2.0 and 1.6 points, with consistent trends under LLM-judge evaluation.
Critical strengths
-
A clear formulation of credit assignment between roles. Coupling the searcher's reward to the generator's abstention avoids penalizing one role for the other's failure. The analysis seperately shows better search accuracy and better answer accuracy given fixed evidence (Figure 2).
-
Consistent results with supporting analysis. DAC is best on average for both backbones under EM and LLM-judge evaluation (Tables 1 and 3). The ablations, the matched comparison with DART (Table 4), and the analysis of over-abstention support the role of each component.
Critical weaknesses
-
It is unclear whether the gains come from RL training or from the prompted inference structure. At inference, DAC is a two-role pipeline built by prompting the same backbone as a searcher and a generator. The paper does not report this pipeline with the untrained backbone, so the benefit of training itself is not quantified. Moreover, with the role decomposition kept and an answer-correctness searcher reward, Qwen3-8B reaches 45.6 average EM (Table 2), identical to single-agent Search-R1 (Table 1). This suggests the cross-verification reward contributes about 1.6 points. An untrained-pipeline baseline would clarify how much of the improvement is attributable to training.
-
Learned abstention is not compared with prompt-only abstention. The generator's abstention is already elicited by its prompt ("answer unknown"; Appendix E). However, the baselines in Figure 5 is never given an abstention option; reaching the turn limit is counted as abstention. Table 8 also lacks a prompted-model reference. A natural control is to replace the co-trained abstention in the searcher reward with a frozen, prompted sufficiency judge. This would test whether co-training abstention, and the hard-positive augmentation needed to counter over-abstention, is necessary.
Questions for authors
-
What is the performance of the DAC pipeline with the untrained backbone (same prompts, abstention disabled) on the Table 1 benchmarks?
-
How does a frozen, prompted abstention judge compare with co-trained abstention, both as a searcher reward and in the Figure 5 and Table 8 analyses?
-
How many runs underlie Tables 1 and 2? Since many margins are within 1–2 points, uncertainty estimates would help. Also, do baseline settings (e.g., top-k, turn limit, answer format) follow the original papers? S3 rises from 14.0 EM to 48.9 under the LLM judge (Tables 1 and 3).
4 comments
Response to Reviewer 9nD9 (2/2)
Q3: Number of runs and uncertainty estimates
Tables 1 and 2 report one training run per method. We have now trained DAC and DART with three training seeds each on Qwen3-8B. The average EM is 47.18 ± 0.05 for DAC and 45.54 ± 0.08 for DART, so the gap of 1.6 points is much larger than the variation between seeds (see "Multi-seed results" in the general response). For Search-R1, the average EM over three runs is 45.52 ± 0.04, 1.7 points below DAC.
Q3: Baseline settings and the S3 scores
We ran all baselines with their public code and evaluated them in the same settings (Appendix C). The only exception is S3's training reward: we used EM, our target evaluation metric, instead of S3's own metric (GenAcc). However, S3 did not improve with training, regardless of this choice. Its paper says that about 15 steps are enough, but in our runs performance did not change between step 0, step 15, and beyond step 100. This held whether we used EM, the LLM judge, or GenAcc as the training reward. For example, on Qwen2.5-7B-Instruct, with GenAcc for both training and evaluation:
| NQ | TriviaQA | PopQA | HotpotQA | 2Wiki | MuSiQue | Bamboogle | Average | |
|---|---|---|---|---|---|---|---|---|
| Step 0 | 63.8 | 76.8 | 55.9 | 53.9 | 46.1 | 19.3 | 5.6 | 45.9 |
| Step 20 | 64.1 | 76.7 | 56.1 | 54.1 | 46.2 | 19.6 | 4.8 | 45.9 |
| Step 100 | 64.4 | 77.1 | 55.9 | 53.8 | 47.0 | 20.2 | 5.6 | 46.3 |
| Step 200 | 64.4 | 76.8 | 55.9 | 54.4 | 47.2 | 20.2 | 4.0 | 46.1 |
In our reproduction, RL training therefore does not change S3's performance. S3's results rather come from its inference pipeline (the decomposed structure and a much more detailed prompt than the other baselines), so in practice it behaves like an inference-time method rather than a training method. This also explains the two scores in Tables 1 and 3: EM is low because the frozen generator never learns the required answer format, and the LLM-judge score is reasonable (although below DAC) but practically the same at step 0 as at step 100.
We thank the reviewer again for the valuable feedback. We hope that these answers resolve the reviewer's concerns. If so, we would be very grateful if the reviewer would kindly reconsider the score. We would be glad to answer any further questions.
Thank you for the detailed response and the additional experiments. My concerns have been addressed, and based on the rebuttal I am raising my rating to 3 (weak acceptance).
Dear Reviewer 9nD9,
Thank you for reading our response carefully and for raising your score. Your comments helped us make the paper clearer and more complete. We appreciate your time and your constructive feedback.
Response to Reviewer 9nD9 (1/2)
We thank the reviewer for the careful review and the constructive questions. We answer each point below, with new experimental results.
W1, Q1: RL training vs. the prompted inference structure
The decomposed inference structure explains only part of the gain. The table below shows the DAC pipeline with the untrained backbone (same prompts, abstention disabled). The "+ DAC" rows give the gain from RL training. On average, RL training adds 7.5 points on Qwen2.5-7B-Instruct and 10.3 points on Qwen3-8B.
W2: Baselines have no abstention option
This is correct. The baselines have no abstention component, so the natural choice is to count continuing to search until the turn limit as abstention.
That DAC abstains better than these baselines is not, by itself, our main claim. With Figure 5, we wanted to show that (1) the abstention that DAC uses as a training tool is learned reasonably well, so it can provide a meaningful signal during training, and (2) it can also serve as an additional feature at test time. The clear gap in the figure shows that DAC's learned abstention is consistently better than what the other methods may have learned implicitly. This supports both points.
W2, Q2: Frozen, prompted abstention judge vs. co-trained abstention
We ran new experiments for this question. The setup and the tables are in "Abstention at test time" and in 3.3 of "Additional ablation study" in the general response. In short: