- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SAVE, a self-compression framework for long-video agentic QA that reduces redundant tool-mediated evidence search. The key idea is to solve a Main Question jointly with a same-video Pressure Question under a shared interaction budget to induce “multi-question pressure,” then extract target-centric single-question supervision by keeping Main- and shared-evidence tool interactions while removing Pressure-only steps; the authors further refine with GRPO where rollouts still include both questions but rewards depend only on the Main Question. Across LVBench, VideoMME (with/without subtitles), and MLVU, SAVE reduces tool calls and token usage by 5–19% with minimal accuracy change, and occasionally improves accuracy (e.g., +2.6 points on MLVU) after RL.
Critical strengths
-
The method addresses a meaningful deployment cost and transfers to single-question inference. SAVE targets unnecessary tool-mediated evidence acquisition, which can reduce both repeated model inputs and tool calls. Its deployment interface requires neither an auxiliary question nor an additional compressor. Table 1 reports consistent tool-call and token reductions across all four evaluation settings, with relatively small accuracy losses in three settings and an improvement on MLVU. This makes the proposed approach practically relevant.
-
The behavioral analysis provides useful evidence about where savings occur. Figure 3 shows reductions concentrated in the long-search tail and in fine-grained caption retrieval, while medium-level retrieval and local video-QA usage remain approximately stable on jointly correct examples. This is more informative than reporting average trajectory length alone and is consistent with reduced repeated probing, although it does not establish the causal mechanism by itself.
Critical weaknesses
-
The trajectory extraction rules need more detail. The authors use the baseline trajectory as a reference, but do not clearly explain how they assign evidence roles or handle useful evidence absent from that trajectory. The coherence evaluation does not establish that the extracted trajectories retain the necessary evidence. Since this extraction step produces SAVE’s supervision, these missing details make it difficult to assess and reproduce a central part of the method.
-
The experiments do not establish the specific benefit of multi-question pressure. The paper lacks matched single-question SFT and GRPO controls, so additional training or data selection could explain some of the gains. During RL, the objective does not reward Pressure-Question correctness, and the authors do not quantify how much search budget that question consumes. These gaps weaken the evidence for the pressure mechanism, which forms the paper’s main contribution and strongly affects my recommendation.
Questions for authors
- How did you choose the 500 MLVU questions? Does this subset reflect the task distribution of the full development set?
- What exact rules do you use to assign evidence roles? How do you handle useful evidence that does not appear in the baseline trajectory?
- Do you have matched single-question SFT and GRPO results using the same training questions and comparable training budgets?
- During RL, how much search budget does the Pressure Question consume? Its accuracy alone does not show whether the agent actively searches for evidence to answer it.
- Do the reductions in tool calls and tokens lead to lower end-to-end inference latency? Can you also report the total training compute, including rollout generation?