- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
WORTH separates whether to acquire evidence from which observations contribute to the answer. After an evidence-verified cold start, it assigns cost-adjusted acquisition credit to the first branch decision and Shapley-based credits to the first plan's requests. Other generated tokens retain the GRPO advantage. Video QA and temporal grounding experiments report improved accuracy with lower inference token use.
Critical strengths
- Controlled accuracy-efficiency gains. Table 4 controls initialization, data, and interface. WORTH reduces the acquisition rate from 92% to 26% and normalized token use from 3.9 to 1.3 while improving accuracy. The alternative-baseline ablation also supports comparing acquisition against answering immediately.
- Credit for redundant evidence. Shapley attribution can share credit between interchangeable observations that leave-one-out attribution would miss (Eq. 6). Assigning that credit to the corresponding request tokens connects supervision to the acquisition decision.
- Evaluation beyond answer accuracy. Tables 2-3 cover video QA and temporal grounding, with grounding also included in Table 4. This tests whether the cheaper acquisition policy retains localization ability, supporting the overall system beyond QA gains.
Critical weaknesses
- Accuracy gains are less pronounced than efficiency gains. In Table 4, normalized token use falls from 3.9 to 1.3, while accuracy improves by 0.4-4.0 percentage points across five QA columns. Observation credit alone adds 0.3-1.5 points. Whether higher inference expenditure could yield further accuracy gains remains unexplored.
- Limited decision-level coverage. New credits apply only to the initial branch and first plan, although episodes allow three plans (Sec. 3.2). Initial acquisition credit includes downstream returns, but later requests receive no separate counterfactual credit. Their frequency, cost, and accuracy contribution are not quantified for the evaluated policy.
- The need for exhaustive attribution is not fully established. The diagnostic analysis motivates accounting for redundant observations, but Table 4 compares observation credit with no observation credit rather than cheaper approximations. It remains unclear whether exhaustive subset enumeration is necessary to obtain the reported accuracy gains.
Questions for authors
- Can WORTH trade its inference savings for higher accuracy? An accuracy-cost curve including Policy and Reader tokens would help. If so, are these results obtained by changing inference settings for the same model, or by retraining with different cost penalties?
- For the evaluated policy, how often are second and third plans used, how much token cost do they add, and what evidence indicates that they improve answer accuracy?
- With acquisition credit unchanged, how does exhaustive Shapley attribution compare with a cheaper approximation, such as sampled Shapley, in accuracy and training cost?
- Table D.3 reports 6.4 minutes per step for WORTH versus 4.8 for GRPO. How much of the added wall-clock time comes from forced continuations, including Reader calls, and from Shapley subset readouts? Please account for overlap from parallel execution.