Anagent For Enhancing Scientific Table & Figure Analysis

TL;DR

This paper introduces Anagent, a multi-agent framework designed to improve the analysis of scientific tables and figures by decomposing tasks, retrieving domain-specific information, synthesizing insights, and iteratively refining results, supported by a large benchmark dataset.

Contribution

The paper presents Anagent, a novel multi-agent system with specialized modules and training strategies, significantly advancing scientific table and figure analysis capabilities.

Findings

Anagent achieves up to 42.12% improvement with finetuning.

Benchmark AnaBench contains 63,178 instances across nine domains.

Task-oriented reasoning is crucial for high-quality analysis.

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/.