most citedCoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

1 citations · 2 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2026

SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

Jingru Guo, Xiangyuan Xue, Lian Zhang +6

Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of expert-level performance. A clos…

cs.CL2026

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems

Rui Ye, Keduan Huang, Qimin Wu +17

LLM-based multi-agent systems (MAS) have demonstrated significant potential in enhancing single LLMs to address complex and diverse tasks in practical applications. Despite conside…

cs.CL2026

Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning

Qinghe Ma, Zhen Zhao, Yiming Wu +3

Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). However, existing studies mainly…

cs.CL2026

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

Yujiong Shen, Yajie Yang, Zhiheng Xi +17

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orches…

cs.CL20261 cited

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

Xiangyuan Xue, Yifan Zhou, Guibin Zhang +7

Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witn…

cs.CL2025

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

Yizhou Wang, Chen Tang, Han Deng +29

We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanni…