- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper identifies two common failure modes in multimodal deep search agents: insufficient active acquisition of external visual evidence and premature lock-in on unverified intermediate hypotheses. First, the authors construct a multimodal entity hypergraph and rewrite entities into implicit visual constraints to synthesize multi-hop QA tasks requiring external image retrieval, which are combined with public datasets to train Qwen3-VL-32B-Thinking via SFT and GRPO. Second, using labels from complete-trajectory auditing, the authors extract a linear "Hypothesis Lock-in Axis" in the model's activation space and design an inference-time controller, HLI-Guard: when the projection score exceeds a threshold, an auxiliary model (GPT-5.6-Luna) is invoked to perform hypothesis extraction, verification prompt injection, context compression, and backtracking. Experiments across five multimodal search benchmarks demonstrate that both model training and inference-time control yield performance gains.
Critical strengths
- Decomposing failures in long-horizon multimodal search into two dimensions (evidence acquisition and hypothesis verification) is intuitive and well-targeted at key bottlenecks.
- The training pipeline yields substantial performance improvements over the base model.
Critical weaknesses
- VeriSeek-VL-FULL relies on a strong proprietary model as an auxiliary controller, leading to an unfair open-source comparison and unquantified overhead. Whenever HLI-Guard is triggered, evidence organization, hypothesis extraction, conflict assessment, and context compression/backtracking are all performed by GPT-5.6-Luna. Consequently, VeriSeek-VL-FULL-32B is in fact a hybrid system combining a 32B model with a proprietary frontier-model controller, making it unfair to directly compare it against purely open-source 7B–32B agents and claim open-source SOTA. It is recommended to include an evaluation where GPT-5.6-Luna is replaced by the 32B model itself.
- Lack of an isolated ablation on the core synthetic dataset. Although the paper presents "hypergraph data synthesis with implicit visual constraints" as a key contribution, there is no ablation comparing training on "public datasets alone (REDMM/LiveVQA/FVQA)" versus "incorporating the synthetic dataset," nor any statistics tracking changes in the frequency of active image-search tool calls before and after training (which I consider an essential behavioral pattern analysis for multimodal search). This ablation is critical for establishing the effectiveness of the proposed data synthesis pipeline.
Questions for authors
Please refer to the Critical Weaknesses above.
Response: open-weight controller, data ablation, and visual search
Thank you for highlighting the controller dependency and the need to isolate our synthetic data's contribution. We have uploaded a revised PDF with an open-weight controller comparison, matched-supervision SFT ablations, and visual search analysis.
Scores below average four independent runs per question. Avg. is the equal-weight mean across the five benchmarks; MMSearch-Plus uses its 221-question single-image subset.
1. Open-weight controller
Following your suggestion, FULL now uses the same final RL 32B checkpoint as both search agent and auxiliary controller for evidence organization, hypothesis extraction, and conflict assessment. We retain Luna as a controller ablation. Both configurations use HLI-Guard at alpha=20% with a 100-turn limit.
The average accuracies are close. In this evaluation, the 32B controller reduces mean end-to-end runtime from 33.05 to 25.81 minutes, saving 7.24 minutes per trajectory (21.9%). Mean trigger counts are also close: 1.194 for Luna and 1.230 for 32B. We therefore use the same 32B checkpoint as the default controller. (Sections 3.1-3.3, Tables 1-2; Appendix C.7.)
2. Contribution of synthetic data
Both SFT models start from Qwen3-VL-32B-Thinking and use the same optimization settings, with 13,919 training and 284 validation trajectories each. We match approximately 69.28M supervised tokens by adjusting the number of updates, counting loss-bearing assistant outputs across all turns. Public-only uses 4,671 REDMM, 6,140 LiveVQA, and 3,392 FVQA trajectories. The full corpus contains 6,669 trajectories from our QA pairs with implicit visual constraints before the training/validation split. Both models use the full toolset and a 40-turn limit.
Our data improves all five benchmarks at matched supervision, adding 9.52 points on average. The largest gains are on MMSearch-Plus (+14.1) and MMBrowseComp (+11.7), where fine-grained visual cues guide retrieval and evidence integration. (Section 3.2; Appendices A.2-A.3.)
3. Active visual search and its task benefit
We measure all 5,252 evaluation trajectories per model. Coverage is the fraction with at least one image-search call; image operations are zoom-in and OCR. Counts are per-trajectory means.
The full mixture raises image-search coverage from 66.1% to 83.7%, while reducing total tool calls from 9.76 to 9.08. Removing TextSearchImage and ImageSearchImage lowers average accuracy by 11.92 points for full SFT (51.58 to 39.66), versus 6.84 for Public-only (42.06 to 35.22). The gap between the models narrows from 9.52 to 4.44 points. Thus, our data improves active visual search and the task benefit obtained from image-search access, with fewer total tool calls. (Appendices A.3-A.4.)