DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue intent-misaligned, under-constrained, or redundant search queries, resulting in poor evidence coverage and accumulating retrieval noise. To mitigate these limitations, we propose QREF, a plug-and-play Query Refiner and Evidence Filter. Specifically, the Query Refiner rewrites search queries according to the current reasoning intent while ensuring complementary coverage across each search batch. The Evidence Filter retains evidence relevant to both the current search batch and the reasoning objective, reducing distracting retrieval results. We initialize the Query Refiner with supervised fine-tuning and optimize it through reinforcement learning based on interactions with a real-world web search environment, reducing ineffective queries. Comprehensive experiments demonstrate that our approach improves the performance of DeepSearch agents across four challenging benchmarks, achieving average relative Pass@1 improvements of 33.55% on WebSailor and 11.04% on TongyiDeepResearch without modifying architectures or retraining their reasoning policies. Compared with the original DeepSearch backbone without QREF, the RL-trained refiner reduces the fraction of query batches that lack discriminative retrieval anchors by 95%. Compared with the SFT-trained refiner, it also lowers the filter-based ineffective query ratio.
Figures & tables
Figure 1: Overview of the QREF integrated into a tool-augmented DeepSearch agent.
Figure 2: Analysis of ineffective queries on WebSailor. (a) Occurrence rates of the three ineffective-query categories before/after query refinement. (b) Cumulative ineffective-query counts for successful and unsuccessful trajectories.
Figure 3: Case study illustrating how the proposed modules refine queries and filter retrieved evidence. (a) Vanilla Search Agent with ineffective intermediate queries. (b) Search Agent with Query Refiner. (c) Search Agent with Query Refiner and Evidence Filter.
Backbone
Method
BrowseComp
BrowseComp-ZH
GAIA
HLE
P@1 ↑
Turns ↓
IQR ↓
P@1 ↑
Turns ↓
IQR ↓
P@1 ↑
Turns ↓
IQR ↓
P@1 ↑
Turns ↓
IQR ↓
Tongyi DeepResearch
Baseline
39.89
46.33
-
39.66
18.10
-
74.36
10.60
-
27.61
11.53
-
+Qwen3-8B
30.65
58.49
59.28
38.41
28.18
34.06
70.69
11.36
51.01
25.53
14.01
55.06
+SFT
44.39
29.57
62.22
48.10
15.59
37.22
74.36
7.77
57.11
28.08
8.81
59.10
+RL(Ours)
45.62
20.46
36.41
49.48
11.50
29.36
77.78
7.51
31.21
27.73
6.07
37.25
+GPT-5.2
46.29
22.23
52.76
51.21
10.15
35.26
79.49
5.97
45.15
27.90
5.67
45.57
Table 1: Main results and search efficiency. P@1 denotes Pass@1. Turns indicates the average number of search turns for WebSailor and search actions for TongyiDeepResearch. IQR denotes the ineffective query ratio (%). Bold and underlined numbers denote the best and second-best results, respectively. ↑ indicates higher is better, and ↓ indicates lower is better.
Method
BrowseComp-ZH
BrowseComp
WebSailor
19.03
10.82
w/o Query Refiner
15.22
13.51
w/o Evidence Filter
22.84
12.88
Full Method
25.26
17.61
Table 2: Ablation study of the proposed modules on WebSailor. w/o Query Refiner retains only the Evidence Filter, whereas w/o Evidence Filter retains only the Query Refiner.
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
Setting
Value
Fine-tuning type
Full-parameter SFT
Maximum length
20,480 tokens
Batch size
2 per device
Gradient accumulation
2 steps
Learning rate
1×10−5
Training epochs
1
Appendix
Table 3: Main hyperparameters used for supervised fine-tuning.
Setting
Value
RL algorithm
PPO with GAE
Training batch size
64
Prompt / response length
2,048 / 2,048 tokens
Actor / critic learning rate
1×10−6 / 1×10−5
PPO mini-batch size
64
Actor / critic micro-batch
1 / 2 per GPU
Appendix
Table 4: Main hyperparameters used for PPO training. TP, PP, and CP denote tensor, pipeline, and context parallelism, respectively.
Method
BC-EN
BC-ZH
HLE
GAIA
Avg@3
18.07
23.99
15.06
48.43
Pass@3
30.15
41.18
25.81
65.51
Appendix
Table 5: Additional WebSailor results with the Query Refinement Module, reported using Avg@3 and Pass@3 .
Trajectory Group
Incorrect
Correct
Total
No failure batches
30
11
41
At least one failure batch
243
16
259
Total
273
27
300
Appendix
Table 6: Contingency table for the χ2 analysis of trajectory correctness versus the presence of ineffective query batches.
Figure 4: Pairwise Pearson correlation matrix for the three ineffective-query categories. The heatmap summarizes the extent to which different query-failure modes co-occur across trajectories.
Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit, unstructured search behavior that causes redundant exploration and brittle evidence aggregation. Motivated by Anthropic's "think" tool paradigm and insights from the information-retrieval literature, we introduce Q+, a set of query and evidence processing tools that make web search more deliberate by guiding query planning, monitoring search progress, and extracting evidence from long web snapshots. We integrate Q+ into the browser sub-agent of Eigent, an open-source, production-ready multi-agent workforce for computer use, yielding EigentSearch-Q+. Across four benchmarks (SimpleQA-Verified, FRAMES, WebWalkerQA, and XBench DeepSearch), Q+ improves Eigent's browser agent benchmark-size-weighted average accuracy by 3.0, 3.8, and 0.6 percentage points (pp) for GPT-4.1, GPT-5.1, and Minimax M2.5 model backends, respectively. Case studies further suggest that EigentSearch-Q+ produces more coherent tool-calling trajectories by making search progress and evidence handling explicit.
Boer Zhang, Mingyan Wu, Dongzhuoran Zhou +6
Meta · Northeastern University, China · University of Oslo +5
Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional hops, and longer trajectories. These global properties, however, are only indirect proxies for the local retrieval capabilities required during search. To address this mismatch, we introduce latent anchor reasoning, which consists of resolving an unnamed retrieval anchor from descriptive specifications and transferring the recovered anchor into a subsequent information demand. This primitive retrieval unit decomposes deep search into chains of coupled operations and organizes question construction around anchor resolution and relation transfer, without prescribing a canonical search path. Based on this formulation, we propose PrimeSeeker, a capability-oriented framework that constructs web-grounded anchor structures and jointly derives a question and a reference evidence skeleton. The skeleton preserves supporting evidence from construction and guides expert generation through extractive highlights of current tool observations. These highlights are removed before supervised fine-tuning, while the skeleton is subsequently reused to audit reference-step coverage for reinforcement-learning rewards. We construct 9,221 expert trajectories, training a 30B search agent. Across five deep-search benchmarks, PrimeSeeker achieves strong performance, while reference-step optimization further improves the supervised policy. The resulting trajectories exhibit low retrieval redundancy, and fixed-budget evaluation shows strong solution coverage with substantially fewer tool calls than long-horizon systems.
Linzhi Peng, Hanting Chen, Heng Chang +3
Beihang University · Huawei Technologies Ltd. · Tsinghua University
Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory. Our trajectory-level analysis reveals a common failure mode in which the agent may encounter an early search state with several plausible directions, but follow one direction before collecting enough comparative evidence. Once this happens, subsequent tool calls tend to reinforce the same path, increasing the chance of failure when the initial direction is misleading. We further find that successful trajectories reduce this risk through two behaviors: grounding vague exploration in concrete candidates and shifting directions when the current path is weak or incomplete. Based on these findings, we propose HypoSearch, which generates lightweight hypotheses as soft search hints, explores them through bounded independent branches, and compares branch-level evidence before commitment. Across four deep-research benchmarks and three backbone models, HypoSearch consistently outperforms single-trajectory search and standard parallel baselines, improving Qwen3.5-122B from 46.7 to 60.0 on BC-small while using fewer tool calls than five independent trajectories. A pilot supervised fine-tuning study further shows that these behavioral signals can curate compact training trajectories and reduce degradation from unfiltered data.
Ruochen Zhou, Zhengyu Chen, Luan Zhang +3
City University of Hong Kong · Meituan · Independent +1