arXiv cs.AI· Xuehang Guo, Zhiyong Lu, Tom Hope, Qingyun Wang·· 14 小时前AI 评分31
Anagent：多智能体框架提升科学表格与图表分析能力
Anagent For Enhancing Scientific Table & Figure Analysis
AI 导读
研究团队提出多智能体框架 Anagent，通过 Planner、Expert、Solver、Critic 四个专用智能体协作完成科学表格与图表分析，并配套监督微调与强化学习的模块化训练策略。
正文 · 原文
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 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: this https URL.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.10081 [cs.CL] |
| (or arXiv:2602.10081v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2602.10081 arXiv-issued DOI via DataCite |
Submission history
From: Xuehang Guo [view email]
[v1]
Tue, 10 Feb 2026 18:46:28 UTC (33,100 KB)
[v2]
Thu, 12 Feb 2026 02:51:40 UTC (33,100 KB)
[v3]
Tue, 27 Oct 2026 18:27:57 UTC (41,098 KB)
来源：arXiv cs.AI · arxiv.org