- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes QRAE, which is an online context-compression method for deep search agents. It uses attention entropy from selected model heads to score retrieved chunks. It adds high-scoring chunks to whitelist and retains lower ones in a recoverable cache. Experiments show reductions in token usage and latency with comparable performance.
Critical strengths
- QRAE addresses an important and practical problem.
- The proposed method achieves consistent token and latency reductions on DeepDiver-7B.
Critical weaknesses
- The paper does not compare alternative scorers within the same context manager. It is unclear whether the gains come from the attention-entropy signal or mainly from the manager.
- The source of the token savings is unclear because compression effects are mixed with cross-step deduplication, fewer searches, and shorter trajectories, which weakens the main efficiency claim.
Questions for authors
- What exactly is Q in the evaluator at each step?
- Does the current trajectory state affect rescoring?
- How do alternative scorers such as Qwen3-Reranker, QRHead, or random scoring perform within the same context manager?
- Are cross-step deduplication and search behavior matched across methods?
- How much of the token reduction comes from context filtering versus fewer search calls and shorter trajectories?
- Please provide the code and data for review.
4 comments
W2 & Q5: Sources of token savings. Compression effects are mixed with cross-step deduplication, fewer searches, and shorter trajectories, leaving the source of token savings unclear and weakening the main efficiency claim. How much of the token reduction comes from context filtering versus fewer search calls and shorter trajectories?
A2: We thank the reviewer for this question. For cross-step deduplication, all evaluated methods share the exact same retrieval configuration and cross-step URL deduplication policy (see Appendix C.3 for details), so deduplication does not contribute to QRAE's relative token savings. Instead, the token reduction comes from two primary sources: (1) reduced per-step input volume, as QRAE selectively admits only high-scoring search chunks into the reasoning context while keeping uncertain candidates outside, and (2) shorter reasoning trajectories, as pruning irrelevant context noise enables the model to better leverage valid evidence and formulate more accurate search queries, thereby reaching the final answer in fewer steps.
To quantify the contribution of each source, we analyzed all trajectories on BrowseComp-Plus with DeepDiver-7B, recording the average cumulative tokens, number of reasoning steps, and per-step context growth:
| Method | Avg. time (s) | Avg. trajectory (tokens) | Avg. steps | Avg. trajectory growth per step (tokens/step) |
|---|---|---|---|---|
| DeepSearch (no compression) | 29.5 | 177k | 18.08 | 763 |
| QRAE (compression) | 20.5 | 54k | 12.07 | 537 |
Based on these statistics, aligning the QRAE's step count to uncompressed baseline's 18.08 steps yields an estimated baseline cost of approximately 78k tokens. Accordingly, out of the total 123k token reduction (), roughly 99k tokens (80.5%) stem directly from context filtering over search results, while roughly 24k tokens (19.5%) come from fewer reasoning and search steps. We have incorporated this breakdown into the revised manuscript.
Q1: What exactly is in the evaluator at each step?
A3: At each step, is always the original user question. By conditioning the evaluator on the original user question, we can filter for chunks that directly support or provide relevant evidence for solving the overall task. We apologize that our notation and wording in Section 3.2 were not sufficiently explicit on this point, and we have revised the manuscript to state this clearly.
Q2: Does the current trajectory state affect rescoring?
A4: No, the current trajectory state does not affect rescoring. The evaluator never uses the agent's previously retrieved context or intermediate reasoning progress as input; instead, it always scores candidate batches conditioned solely on the original user question . Which chunks are selected for rescoring is determined strictly by their historical evaluation count, prioritizing candidates with the fewest prior evaluations.
Q4: Are cross-step deduplication and search behavior matched across methods?
A5: Yes, both cross-step deduplication and the underlying search framework are completely matched across all methods to ensure a fair comparison. Specifically, cross-step URL deduplication is consistently applied across every baseline and QRAE. Moreover, all methods follow the same Tongyi-DeepResearch agent framework and preserve the model's original think-act loop, without altering how the agent generates search actions.
Q6: Please provide the code and data for review.
A6: We have uploaded the core implementation reproducing our main results (Table 1) to an anonymous repository for review: https://anonymous.4open.science/r/QRAE-A337/. The remaining code, including offline head localization, experiments on the 30B or 92B model, and ablation studies, will be publicly released upon acceptance of the paper.
Response from Reviewer SJWm
Thank you for the detailed response and the new experiments. I still have several concerns.
-
Changed ablation numbers. In Table 5, the BrowseComp-Plus "Current-search filtering" row changed from 14.9 / 30.2 s / 129k to 15.4 / 27.6 s / 78k. It is not highlighted. The new numbers match the rebuttal's "QRAE (filtering only)". Please explain why this result changed.
-
Token differences under the same manager. In Table 6, all scorers share the same manager and admit the same number of chunks per trigger. The per-step admitted volume should therefore be similar, yet QRAE uses 54k tokens and Qwen3-Reranker uses 139k. Please report the average number of steps, search calls, and admitted-chunk length for each scorer. Normalized entropy is length-sensitive (App. E.3), so QRAE may simply prefer shorter chunks.
-
Token-saving decomposition. The 78k reference in D.9 seems to come from linear scaling. Because context accumulates, later steps cost more than average ones. With your reported growth of 537 tokens/step, 18.08 steps would give roughly 100–110k. That would put the split closer to 55/45 than 80/20. Please give the exact procedure, or compare cumulative tokens at matched step indices directly.
-
Evaluator token count. Table 21 reports 4.9k compression tokens per BrowseComp-Plus trajectory. Table 15 reports 4.36 delayed admissions per trajectory with 3 admissions per trigger, which implies at least about 2.4 triggers on average. Each trigger runs two prefills over 5 chunks of up to 512 tokens. This suggests at least about 10k evaluator tokens. In the released code, the probe calls are also not added to
token_usage. How were evaluator tokens measured, and are they included in Table 1? -
Rescoring. Since Q is fixed and the trajectory state is not used, a chunk's score changes only through batch composition. The paper still says chunks are reevaluated "when later evidence changes their utility" (Sec. 1, App. A.1). The score-once gains in Table 23 (0.2–0.7 pp, single run) are within the CI widths in Table 19. Please revise these claims.
-
Cross-model claims. Table 19 shows no significant gain over DeepSearch on the 30B and 92B models. The abstract and conclusion still state "2.35 pp" and "benefits generalize to ~100B". The new claim about preliminary 200-step experiments (D.3) has no supporting data and should be removed or substantiated.
-
Code. The BrowseComp-Plus README uses 256-token snippets and 20 turns, while the paper uses 512 tokens and 50 rounds. The baselines and the Table 6 variants are not included.
Thus, I keep my score.
All scorers use the same context manager and admission quota, and the retained chunks are comparable in length. We attribute the efficiency gap to how the selected evidence shapes the agent’s subsequent steps. QRAE selects chunks that more directly support the original query, helping the model draw more accurate inferences and choose more effective search actions. The agent therefore spends fewer think–act steps pursuing false leads. Each avoided step saves another pass over the growing context, substantially reducing token use and latency. This is consistent with context rot, where distracting passages can derail reasoning even when the necessary evidence is present.
Our central finding is that reasoning models encode a relevance signal in their own attention. We found this signal in all five models tested, and it became more discriminative with scale. The 7B or 30B or 92B model’s own signal outperformed a 0.6B reranker trained specifically for relevance scoring. DeepSearch context management is one application of this broader idea. By understanding how a model recognizes useful evidence, we can use that ability to improve its reasoning.
You can run the public anonymous code to evaluate QRAE directly and investigate the empirical questions you raised about evidence selection. The release predates the final implementation, but it uses exactly the same attention heads identified in DeepDiver-7B, L18H22 and L17H0. A single search is enough to inspect the signal. Run a search, examine how these heads respond to the returned chunks, and check whether QRAE ranks supporting evidence above distractors. The signal is visible regardless of the agent’s turn limit or how many chunks it subsequently admits. We released the code so readers can test whether QRAE reliably identifies useful evidence and whether using that evidence helps the model solve real search tasks.
Our goal is to improve model performance by understanding how a model recognizes useful evidence and putting that ability to work. DeepSearch context management is one concrete application. The agent framework and engineering optimizations fall outside the main focus of our work.
We sincerely thank the reviewer for the detailed feedback, which has helped us further strengthen the demonstration of our method's practicality and effectiveness. Below, we provide our detailed point-by-point responses to each comment. For ease of reference, all corresponding revisions in the updated manuscript are highlighted in blue. Please feel free to let us know if any further clarification is needed.
A1: We sincerely thank the reviewer for pointing out this limitation. We agree that holding the context-management policy fixed is essential to isolate the contribution of the entropy-based scoring signal. Following your suggestion, we evaluated alternative scorers on BrowseComp-Plus across DeepDiver-7B, OpenResearcher-30B, and OpenPangu-2.0-Flash-92B (spanning 7B to nearly 100B parameters and diverse architectures) under the exact same QRAE context-management framework (identical persistent whitelist, candidate cache, reevaluation schedule, and retention budget). Specifically, we compare
QRAEwithQwen3-RerankerandQRHead (full scoring)(the baselines from our paper),Retrieval order(selecting top-ranked chunks by their returned search order), andAttention sum(using the summed positive attention):Under the identical context manager,
QRAEconsistently achieves higher task success and substantially lower latency and token usage than all alternative signals across all three models, demonstrating the clear superiority of our entropy-based scoring signal.Conversely, we also conducted the reverse comparison by stripping away QRAE's cache-and-whitelist manager and applying the QRAE signal solely to filter chunks within each individual search (
QRAE (filtering only)), matching the per-search filtering setup ofRerankandQRHeadin the paper:Even under simple per-search filtering without the context manager,
QRAE (filtering only)consistently outperformsRerankandQRHeadacross all models in both accuracy and efficiency, further confirming the robustness of the QRAE signal. Moreover, comparingQRAE (filtering only)with the fullQRAEin the first table shows that our context-management framework provides complementary gains: by ranking candidates globally across the cache rather than truncating within each individual search, it prevents relevant chunks from being permanently discarded when a single search returns more useful chunks than the per-step quota allows. We have incorporated the controlled comparison of different scoring signals under the same context-management framework into the ablation study in Section 4.4 of the revised manuscript.