Anagent For Enhancing Scientific Table & Figure Analysis

• URL: http://arxiv.org/abs/2602.10081v2
• Date: Thu, 12 Feb 2026 02:51:40 GMT
• Title: Anagent For Enhancing Scientific Table & Figure Analysis
• Abstract summary: Anagent is a framework for enhanced scientific table & figure analysis through four specialized agents.<n>Anagent achieves substantial improvements across 9 broad domains with 170 domains.<n>We show that task-oriented reasoning and context-aware problem-solving are essential for high-quality scientific table & figure analysis.
• Score: 13.604302149501557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In scientific research, analysis requires accurately interpreting complex multimodal knowledge, integrating evidence from different sources, and drawing inferences grounded in domain-specific knowledge. However, current artificial intelligence (AI) systems struggle to consistently demonstrate such capabilities. The complexity and variability of scientific tables and figures, combined with heterogeneous structures and long-context requirements, pose fundamental obstacles to scientific table \& figure analysis. To quantify these challenges, we introduce AnaBench, a large-scale benchmark featuring $63,178$ instances from nine scientific domains, systematically categorized along seven complexity dimensions. To tackle these challenges, we propose Anagent, a multi-agent framework for enhanced scientific table \& figure analysis through four specialized agents: Planner decomposes tasks into actionable subtasks, Expert retrieves task-specific information through targeted tool execution, Solver synthesizes information to generate coherent analysis, and Critic performs iterative refinement through five-dimensional quality assessment. We further develop modular training strategies that leverage supervised finetuning and specialized reinforcement learning to optimize individual capabilities while maintaining effective collaboration. Comprehensive evaluation across 9 broad domains with 170 subdomains demonstrates that Anagent achieves substantial improvements, up to $\uparrow 13.43\%$ in training-free settings and $\uparrow 42.12\%$ with finetuning, while revealing that task-oriented reasoning and context-aware problem-solving are essential for high-quality scientific table \& figure analysis. Our project page: https://xhguo7.github.io/Anagent/.

Related papers

• SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration [46.64739473662869]
  We introduce SciExplore, a benchmark designed to evaluate scientific information-seeking and reasoning capabilities of LLMs and agents.<n> SciExplore comprises four task types covering 103 expert-curated tasks across more than ten scientific disciplines.<n>We evaluate over ten state-of-the-art LLMs and autonomous agents on SciExplore, revealing substantial performance gaps with performance degrading sharply as task complexity increases and extremely low accuracy on the most challenging structured tasks.
  arXiv  Detail & Related papers  (2026-07-23T05:17:00Z)
• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• Towards Knowledgeable Deep Research: Framework and Benchmark [105.87257445617922]
  This paper introduces Knowledgeable Deep Research (KDR), which requires DR agents to generate reports with both structured and unstructured knowledge.<n>We propose the Hybrid Knowledge Analysis framework (HKA), a multi-agent architecture that integrates texts, figures, and tables into coherent multimodal reports.<n> Experimental results demonstrate that HKA consistently outperforms most existing DR agents on general-purpose and knowledge-centric metrics.
  arXiv  Detail & Related papers  (2026-04-09T02:06:27Z)
• Pitfalls in Evaluating Interpretability Agents [91.49742416116635]
  We build an agentic system in which a research agent iteratively designs experiments and refines hypotheses.<n>Our work demonstrates fundamental challenges in evaluating complex automated interpretability systems.
  arXiv  Detail & Related papers  (2026-03-20T16:27:17Z)
• A Cloud-based Multi-Agentic Workflow for Science [0.12314765641075438]
  Large Language Models (LLMs) become ubiquitous across various scientific domains.<n>Their lack of ability to perform complex tasks like running simulations or to make complex decisions limits their utility.<n>We present a domain-agnostic, model-independent workflow for an agentic framework that can act as a scientific assistant while being run entirely on cloud.
  arXiv  Detail & Related papers  (2026-01-18T22:37:09Z)
• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning [0.054619385369457214]
  We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents.<n>Each agent generates hypothetical passages to optimize retrieval for its analytic perspective, ensuring knowledge integration is both context-sensitive and computation-efficient.<n>Our results demonstrate that multi-agent, on-demand knowledge integration significantly enhances both reasoning accuracy and efficiency, offering a scalable approach for complex, knowledge-intensive problem-solving.
  arXiv  Detail & Related papers  (2025-10-31T15:51:00Z)
• AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite [75.58737079136942]
  We present AstaBench, a suite that provides the first holistic measure of agentic ability to perform scientific research.<n>Our suite comes with the first scientific research environment with production-grade search tools.<n>Our evaluation of 57 agents across 22 agent classes reveals several interesting findings.
  arXiv  Detail & Related papers  (2025-10-24T17:10:26Z)
• InferA: A Smart Assistant for Cosmological Ensemble Data [0.5130440339897478]
  InferA is a multi-agent system that enables scalable and efficient scientific data analysis.<n>At the core of the architecture is a supervisor agent that orchestrates a team of specialized agents responsible for distinct phases of the data retrieval and analysis.<n>To demonstrate the framework's usability, we evaluate the system using ensemble runs from the HACC cosmology simulation which comprises several terabytes.
  arXiv  Detail & Related papers  (2025-10-14T18:47:22Z)
• Scaling Generalist Data-Analytic Agents [95.05161133349242]
  DataMind is a scalable data synthesis and agent training recipe designed to build generalist data-analytic agents.<n>DataMind tackles three key challenges in building open-source data-analytic agents.
  arXiv  Detail & Related papers  (2025-09-29T17:23:08Z)
• EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis [0.0]
  Large Language Models (LLMs) offer new opportunities to automate complex interdisciplinary research.<n>EpidemIQs is a novel multi-agent LLM framework that integrates user inputs and autonomously conducts literature review, analytical derivation, network modeling, invoking simulations, data visualization and analysis, and finally documentation of findings in a structured manuscript.<n>We evaluate EpidemIQs across different scenarios measuring computational cost, completion success rate, and AI and human expert reviews of generated reports.
  arXiv  Detail & Related papers  (2025-09-24T18:54:56Z)
• Deep Research Agents: A Systematic Examination And Roadmap [109.53237992384872]
  Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
  arXiv  Detail & Related papers  (2025-06-22T16:52:48Z)
• Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks [94.19506319646376]
  We introduce Agent-X, a benchmark for evaluating vision-centric agents in real-world, multimodal settings.<n>Agent-X features 828 agentic tasks with authentic visual contexts, including images, multi-image comparisons, videos, and instructional text.<n>Our results reveal that even the best-performing models, including GPT, Gemini, and Qwen families, struggle to solve multi-step vision tasks.
  arXiv  Detail & Related papers  (2025-05-30T17:59:53Z)
• OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI [73.75520820608232]
  We introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities.<n>These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage.<n>Our evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration.
  arXiv  Detail & Related papers  (2024-06-18T16:20:53Z)
• A Taxonomy and Archetypes of Business Analytics in Smart Manufacturing [0.0]
  Business analytics is a key driver for smart manufacturing. However, researchers and practitioners struggle to keep track of the progress and acquire new knowledge within the field. We develop a quadripartite taxonomy as well as to derive archetypes of business analytics in smart manufacturing.
  arXiv  Detail & Related papers  (2021-10-12T16:13:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.