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.
@article{arxiv.2605.05407,
title = {PRISM: Perception Reasoning Interleaved for Sequential Decision Making},
author = {Mohamed Salim Aissi and Clemence Grislain and Clement Romac and Laure Soulier and Mohamed Chetouani and Olivier Sigaud and Nicolas Thome},
journal= {arXiv preprint arXiv:2605.05407},
year = {2026}
}