# EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

arXiv: https://arxiv.org/abs/2604.05557 · HTML: https://mlsanity.com/paper/2604.05557/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs](https://mlsanity.com/paper/2406.11833/) (2024)
- [SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers](https://mlsanity.com/paper/2407.09413/) (2024)
- [SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs](https://mlsanity.com/paper/2308.03349/) (2023)
- [MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents](https://mlsanity.com/paper/2508.21475/) (2025)
- [Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models](https://mlsanity.com/paper/2602.02185/) (2026)
- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content](https://mlsanity.com/paper/2410.10783/) (2024)
- [MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning](https://mlsanity.com/paper/2503.18533/) (2025)
- [PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature](https://mlsanity.com/paper/2510.10909/) (2025)
- [Memory-QA: Answering Recall Questions Based on Multimodal Memories](https://mlsanity.com/paper/2509.18436/) (2025)
- [MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models](https://mlsanity.com/paper/2510.16641/) (2025)
- [am-ELO: A Stable Framework for Arena-based LLM Evaluation](https://mlsanity.com/paper/2505.03475/) (2025)
- [VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors](https://mlsanity.com/paper/2512.06759/) (2025)
- [SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature](https://mlsanity.com/paper/2601.10108/) (2026)
- [Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling](https://mlsanity.com/paper/2507.06183/) (2025)
- [Efficient Multimodal Planning Agent for Visual Question-Answering](https://mlsanity.com/paper/2601.20676/) (2026)
- [AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings](https://mlsanity.com/paper/2509.09470/) (2025)

## Built on by (most cited first, 2 of 2)

- [Claw AI Lab: An Autonomous Multi-Agent Research Team](https://mlsanity.com/paper/2605.22662/) (2026)
- [TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents](https://mlsanity.com/paper/2605.09934/) (2026)

## Abstract (arXiv)

Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across papers to align experimental settings and support reproducible conclusions. This joint capability is not systematically assessed in existing benchmarks, which largely under-evaluate proactive search, multi-evidence integration and sustained evidence use over time. In this work, we introduce EpiBench, an episodic multi-turn multimodal benchmark that instantiates short research workflows. Given a research task, agents must navigate across papers over multiple turns, align evidence from figures and tables, and use the accumulated evidence in the memory to answer objective questions that require cross paper comparisons and multi-figure integration. EpiBench introduces a process-level evaluation framework for fine-grained testing and diagnosis of research agents. Our experiments show that even the leading model achieves an accuracy of only 29.23% on the hard split, indicating substantial room for improvement in multi-turn, multi-evidence research workflows, providing an evaluation platform for verifiable and reproducible research agents.