- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces a method to rewrite, decompose, or disambiguate low-confidence queries to improve retrieval in search agents.
Critical strengths
The method is simple and training-free, which could help improve performance.
Critical weaknesses
- The evaluation is limited. They use saturated benchmarks (back in 2018) to support their claims. In addition, they only use a subset of 200 examples and run the evaluation once, so the results are within noise. We do not know whether the improvements are real. The paper also does not state the backbone model used in the experiments, making their setup unclear.
- Unclear how the mechanism helps improve retrieval. The paper does not give information about how frequently the agent rewrites its queries, and the effect on those questions.
- The method can be replaced by training RL on the backbone, allowing it to make clearer queries.
Questions for authors
- What model backbone did you use in the experiments?
- How often the agent has to rewrite their queries?
- Why did you use different seeds (42/40)?
6 comments
Part 2 of 2
W2/Q2. Query-refinement mechanism, intervention frequency, and effects on retrieval
Mechanism. QC$\rightarrow$QR intervenes before retrieval when the minimum query-token confidence falls below the agent-specific threshold. It generates rewrite, decompose, and disambiguate candidates, selects the candidate with the highest minimum-token confidence, and submits that query to the same retriever. The agent then continues reasoning using the retrieved evidence. Thus, the intervention changes the search query while keeping the retriever and search-agent weights fixed.
Refinement frequency. Appendix G.2, Table 12 reports the following intervention rates:
| Agent | Search queries refined |
|---|---|
| Search-R1 | 31.30% |
| R1-Searcher | 11.23% |
| HiPRAG | 47.78% |
| ReSearch | 25.37% |
These percentages refer to search queries rather than questions because a question may involve multiple search queries.
Effect on retrieval. The paper provides two complementary analyses. First, below-threshold queries have lower gold-document Hit@1 than above-threshold queries:
| Agent | Below threshold | Above threshold |
|---|---|---|
| Search-R1 | 40.4% | 48.7% |
| R1-Searcher | 34.7% | 49.4% |
| HiPRAG | 20.0% | 41.7% |
| ReSearch | 36.8% | 42.4% |
These results support using confidence to identify queries associated with weaker retrieval.
Second, Table 3 compares retrieval before and after QC$\rightarrow$QR. Gold-document Hit@1 improves across all four agents and all three multi-hop datasets:
| Agent | HotpotQA Hit@1 | 2Wiki Hit@1 | MuSiQue Hit@1 |
|---|---|---|---|
| Search-R1 | 62.80 70.20 | 63.20 69.00 | 49.00 58.00 |
| R1-Searcher | 74.00 75.00 | 76.50 78.50 | 61.50 63.50 |
| HiPRAG | 65.50 73.00 | 63.50 69.50 | 45.19 53.33 |
| ReSearch | 79.38 83.51 | 78.00 80.00 | 59.50 62.00 |
Hit@3 also improves in every reported comparison, by 1.00–7.41 percentage points. Table 5 provides complementary evidence of reduced repetitive retrieval; for example, Search-R1's NovelRate@1 on NQ increases from 72.81% to 88.70%.
W3. Inference-time query repair versus additional reinforcement learning
Our motivation, however, is to improve already-trained search agents without requiring another computationally expensive training cycle for each backbone.
As discussed in the Introduction and Appendix D, training-based approaches such as Search-R1, ReSearch, R1-Searcher, and HiPRAG modify the agent's parameters. QC$\rightarrow$QR instead operates entirely at inference time: it uses the agent's existing token probabilities to identify uncertain search queries and an off-the-shelf reformulator to repair them before retrieval. Neither the search agent nor the retriever is retrained, and no additional reward-model training or RL rollouts are required.
This distinction is useful when deploying existing checkpoints or applying query refinement across different agents. We evaluate the same intervention framework on Search-R1, R1-Searcher, ReSearch, and HiPRAG, covering agents trained with both outcome-based and process-based rewards. The improvements on HiPRAG further suggest that inference-time refinement can provide benefits even after process-supervised RL training.
Q3. Consistent random seeds across experiments
We use the same three seeds 40, 41, and 42 for all experiments and report the mean sample standard deviation across these runs.
We sincerely thank the reviewer again for the careful and constructive review. We hope that the clarifications and additional experiments address the concerns raised, and we would be happy to provide any further clarification. If the concerns have been satisfactorily addressed, we would be grateful if the reviewer could kindly reconsider the evaluation score.
I appreciate the authors' responses and clarification. They addressed my concern about the results' significant. However, it's still unclear:
- Where the gains come from: in the Hit@1 improvement, how often does it turn incorrect answers into correct?
- In addition, how you decide the threshold ? Why do we need rewriting instead of making a model issue effective queries at first?
- How often the refinement at example-level?
Part 1 of 2
W1/Q1. Evaluation scope, multi-seed results, and backbone specifications
We thank the reviewer for raising these concerns. We use the standard NQ, HotpotQA, 2Wiki, and MuSiQue benchmarks with the Wikipedia-2018 corpus to maintain a controlled comparison with established search agents works (Search-R1, ReSearch, R1-Searcher, HIPRAG). The 2018 date refers to the Wikipedia retrieval corpus, rather than the release date of all evaluation benchmarks. These experiments assess refinement under a controlled retrieval environment. The paper additionally evaluates on GAIA and WebWalkerQA using web search, providing evidence beyond the fixed Wikipedia index
To assess stability, we repeat QR (First) and QR (All) using seeds 40, 41, and 42 and report the mean ± sample standard deviation:
We also clarify the backbone configurations:
The Direct, CoT, RAG, and IRCoT baselines use Qwen2.5-3B-Instruct (3B parameters). We will add these specifications and the multi-seed results to the revised manuscript.