paper-with-me

홈 › Papers

PRISM: Perception Reasoning Interleaved for Sequential Decision Making

2026-05-06 · Mohamed Salim Aissi, Clemence Grislain, Clement Romac, Laure Soulier, Mohamed Chetouani, Olivier Sigaud, Nicolas Thome arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.05407

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

2024-06-20 · Yuxuan Qiao, Haodong Duan, Xinyu Fang, Junming Yang 외

Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is…

Language ModellingLarge Language Model

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling

2025-12-05 · Shuai Dong, Siyuan Wang, Xingyu Liu, Chenglin Li 외 arxiv

Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, lat…

Multimodal ReasoningVisual Reasoning

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

2026-07-04 · Zican Hu, Xuyang Hu, Yiming Liu, Zuwei Long 외 hf

Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Exist…

Reinforcement LearningSpatial ReasoningImage GenerationImage Denoising

PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning

2025-03-13 · Yirong Sun, Yanjun Chen

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core,…

Autonomous NavigationDecision MakingLanguage ModelingLanguage Modelling+2

PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments

2026-05-12 · Yunn Kang Lim, Pengzhan Sun, Ziyi Bai, Xun Xu 외 arxiv

When an LLM-based embodied agent fails at a household task, the culprit could be misidentified objects, forgotten sub-goals, or poor action sequencing -- yet existing benchmarks report only a single success rate, making …