PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Daoyu, Cheng, Mingyue, Yu, Shuo, Liu, Zirui, Guo, Ze, Li, Xin, Liu, Qi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918314002874368
author Wang, Daoyu
Cheng, Mingyue
Yu, Shuo
Liu, Zirui
Guo, Ze
Li, Xin
Liu, Qi
author_facet Wang, Daoyu
Cheng, Mingyue
Yu, Shuo
Liu, Zirui
Guo, Ze
Li, Xin
Liu, Qi
contents Understanding and reasoning on the large-scale scientific literature is a crucial touchstone for large language model (LLM) based agents. However, existing works are mainly restricted to tool-free tasks within single papers, largely due to the lack of a benchmark that evaluates cross-paper reasoning and multi-tool orchestration in authentic research scenarios. In this work, we propose PaperArena, a benchmark to evaluate LLM-based agents on questions that require integrating information across multiple papers with the assistance of external tools. Given a research question, agents should formulate a reasoning plan, interact with multiple papers, and invoke appropriate tools to produce a well-grounded answer. To support standardized evaluation, we provide a platform for agent execution, offering a modular tool environment including multimodal parsing, context retrieval, and programmatic computation. Experiments reveal that even the leading LLM powering a well-established agentic workflow achieves merely 38.78% average accuracy, while on the hard subset, accuracy drops to only 18.47%. We also analyze reasoning traces and diagnose agent behavior, providing the community with insights to develop and evaluate more capable scientific agents.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10909
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
Wang, Daoyu
Cheng, Mingyue
Yu, Shuo
Liu, Zirui
Guo, Ze
Li, Xin
Liu, Qi
Artificial Intelligence
Understanding and reasoning on the large-scale scientific literature is a crucial touchstone for large language model (LLM) based agents. However, existing works are mainly restricted to tool-free tasks within single papers, largely due to the lack of a benchmark that evaluates cross-paper reasoning and multi-tool orchestration in authentic research scenarios. In this work, we propose PaperArena, a benchmark to evaluate LLM-based agents on questions that require integrating information across multiple papers with the assistance of external tools. Given a research question, agents should formulate a reasoning plan, interact with multiple papers, and invoke appropriate tools to produce a well-grounded answer. To support standardized evaluation, we provide a platform for agent execution, offering a modular tool environment including multimodal parsing, context retrieval, and programmatic computation. Experiments reveal that even the leading LLM powering a well-established agentic workflow achieves merely 38.78% average accuracy, while on the hard subset, accuracy drops to only 18.47%. We also analyze reasoning traces and diagnose agent behavior, providing the community with insights to develop and evaluate more capable scientific agents.
title PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
topic Artificial Intelligence
url https://arxiv.org/abs/2510.10909