PRISM: Perception Reasoning Interleaved for Sequential Decision Making.
Mohamed AISSI, Clémence, Clément Romac, Laure Soulier, Mohamed Chetouani, Olivier Sigaud, Nicolas THOME
Abstract
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.
BibTeX
@inproceedings{
aissi2026prism,
title={{PRISM}: Perception Reasoning Interleaved for Sequential Decision Making.},
author={Mohamed Salim AISSI and Cl{\'e}mence Grislain and Cl{\'e}ment ROMAC and Laure Soulier and Mohamed CHETOUANI and Olivier Sigaud and Nicolas THOME},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=shdJbVmwrp}
}