PRISM: Perception Reasoning Interleaved for Sequential Decision Making
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909019874000896 |
|---|---|
| author | Aissi, Mohamed Salim Grislain, Clemence Romac, Clement Soulier, Laure Chetouani, Mohamed Sigaud, Olivier Thome, Nicolas |
| author_facet | Aissi, Mohamed Salim Grislain, Clemence Romac, Clement Soulier, Laure Chetouani, Mohamed Sigaud, Olivier Thome, Nicolas |
| contents | Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question-answer (DQA) pipeline. Instead of passively accepting the VLM's description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05407 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRISM: Perception Reasoning Interleaved for Sequential Decision Making Aissi, Mohamed Salim Grislain, Clemence Romac, Clement Soulier, Laure Chetouani, Mohamed Sigaud, Olivier Thome, Nicolas Artificial Intelligence Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question-answer (DQA) pipeline. Instead of passively accepting the VLM's description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers. |
| title | PRISM: Perception Reasoning Interleaved for Sequential Decision Making |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.05407 |