paper-with-me

Papers

See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs

2026-08-28 · Sarang Manoj Pekhale, Amartya Roy, Rajat Sarkar, Souvik Chakraborty arxiv

Discovering governing partial differential equations (PDEs) from observational data remains a core challenge across the sciences. Existing sparse-regression, symbolic-regression, and LLM-based approaches can be constrained by predefined libraries, noise sensitivity, hallucination, or limited iterative refinement. We introduce \textbf{MAGE} (\textbf{M}ultimodal \textbf{A}gentic \textbf{G}overning \textbf{E}quation Discovery), an agentic framework that organizes PDE discovery as a \textit{confidence governed hypothesis validation loop} inspired by the scientific cycle of observation, hypothesis, and falsification. Four role-specialized agents collaborate: a \textit{Differential Observer} computing derivatives and diagnostic visualizations; a VLM-powered \textit{Phenomenology Extractor} distilling qualitative cues from multimodal diagnostics; an LLM-driven \textit{Governing Law Synthesizer} proposing candidates without a predefined library; and an \textit{Equation Arbiter} fitting coefficients and assigning confidence scores. Discovery iterates until the top candidate clears a user-specified threshold, providing a structured process with an explicit accept-reject protocol. On the evaluated canonical PDE suite, MAGE obtains \textbf{8/8} exact structural recovery and the lowest coefficient error among the compared methods on \textbf{7/8} systems, with improvements of up to \textbf{4 orders of magnitude} and a geometric-mean improvement of approximately \textbf{3 orders of magnitude}. The pipeline also recovers the expected operators in two complex geometries and, on one laboratory sensor record, selects a cubic restoring-force model with held-out $R^2=0.98538$. These results support further study of structured agentic reasoning for library-free governing-law discovery, while broader generalization remains to be evaluated.

📄 PDF Abstract BibTeX arXiv:2608.27869

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning

2025-08-14 · Yushi Feng, Junye Du, Yingying Hong, Qifan Wang 외 arxiv

Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently …

Reinforcement LearningSemantic Similarity

UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale

2025-11-22 · Shengyuan Wang, Zhiheng Zheng, Yu Shang, Lixuan He 외 arxiv

The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality…

3D Generation

Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch

2025-12-02 · Yifan Zhang, Liang Hu, Haofeng Sun, Peiyu Wang 외 arxiv

Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcement learning, and lack planning grounded…

Reinforcement LearningImage Manipulation

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning

2026-05-19 · Juncheng Wu, Letian Zhang, Yuhan Wang, Haoqin Tu 외 arxiv

Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and handed to the model. Real-world clinical wor…

CollEX -- A Multimodal Agentic RAG System Enabling Interactive Exploration of Scientific Collections

2025-04-10 · Florian Schneider, Narges Baba Ahmadi, Niloufar Baba Ahmadi, Iris Vogel 외

In this paper, we introduce CollEx, an innovative multimodal agentic Retrieval-Augmented Generation (RAG) system designed to enhance interactive exploration of extensive scientific collections. Given the overwhelming vol…

RAGRetrieval-augmented Generation