- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes Omni-Decision, an omni-modal agent that uses a typed evidence ledger to track unresolved needs, verified facts, and conflicts. A planner, critic, and reducer share this state to guide evidence acquisition and finalization. The system is evaluated on OmniGAIA and WorldSense, and its trajectories support supervised fine-tuning and decision-level reinforcement learning.
Critical strengths
- The evidence ledger provides a clear way to track missing information and conflicting evidence across heterogeneous tool outputs, whihc provides a useful design for tasks requiring several dependent evidence-gathering steps.
- The experiments cover both open-world evidence seeking and question answering. The competitive results and measured computational costs demonstrate the system’s practical performance.
- The recorded states, actions, and verdicts provide reusable supervision without step-level manual annotation. Training weaker planners on these trajectories is a useful extension of the inference framework.
Critical weaknesses
- The evidence-readiness mechanism is not consistently described across the method and prompts. Allowing answers despite insufficient evidence metadata and permitting forced finalization leave the scope of the claimed evidence-closure control unclear.
- The authors can also discuss if the planner makes the wrong decision at the beginning, and the way to mitigate the impact.
- The insights of the LEDGER can be detailed and made clearer. For example, if it helps drop unrelated information, and if it help models make new and correct plans.
Questions for authors
See weaknesses.
Dear Area Chair and Authors,
I would appreciate it if the Area Chair could first confirm whether the submission complies with the ICLR 2027 formatting requirements. I have raised this question in previous confidential comments and would welcome clarification.
Thank you to the authors for their response. My remaining concern is whether a tool call that receives a higher reward is more likely to return correct evidence. In Table 4, adding RL to SFT yields a net gain of three correct answers across the 238 held-out Medium and Hard questions. The planner could achieve this gain by learning when to keep searching, even if its ability to choose an effective tool call stays the same. This distinction matters because alignment with the teacher’s reference decision accounts for 60% of the reward.