Anagent For Enhancing Scientific Table & Figure Analysis
cs.CL, cs.AI
Submitted: 2026-02-10
Updated: 2026-10-27
Project page: https://xhguo7.github.io/Anagent
License: http://creativecommons.org/licenses/by/4.0/
The gist: In scientific research, analysis requires accurately interpreting complex multimodal knowledge, integrating evidence from different sources…
Terminology
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 13.43% in training-free settings and 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/.
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
- TabArena: A Living Benchmark for Machine Learning on Tabular Data
- Accelerating scientific discovery with Co-Scientist
- Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
- SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
- WildSci: Advancing Scientific Reasoning from In-the-Wild Literature
- CiteME: Can Language Models Accurately Cite Scientific Claims?
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Perception-Aware Policy Optimization for Multimodal Reasoning
- From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data