Cover Image

Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Xiaohan, Feng, Shiyang, Huang, Songtao, Bai, Lei, Wang, Bin, Zhang, Bo
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bench-CoE: a Framework for Collaboration of Experts from Benchmark
by: Wang, Yuanshuai, et al.
Published: (2024)

CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering
by: Zhao, Jinkun, et al.
Published: (2025)

CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory
by: Suo, Jiashun, et al.
Published: (2025)

CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems
by: Sun, Kangkang, et al.
Published: (2026)

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification
by: Yu, Wenlong, et al.
Published: (2025)

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
by: Huang, Jiahao, et al.
Published: (2026)

CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents
by: Yu, Ziyang, et al.
Published: (2026)

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
by: Baumgärtner, Tim, et al.
Published: (2026)

CoEx -- Co-evolving World-model and Exploration
by: Kim, Minsoo, et al.
Published: (2025)

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
by: Deng, Andong, et al.
Published: (2025)

SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
by: Sehwag, Udari Madhushani, et al.
Published: (2026)

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
by: Pan, Teng, et al.
Published: (2026)

SciFig: Towards Automating Scientific Figure Generation
by: Huang, Siyuan, et al.
Published: (2026)

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
by: Li, Xuchen, et al.
Published: (2025)

Grounding LLMs in Scientific Discovery via Embodied Actions
by: Zhang, Bo, et al.
Published: (2026)

SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning
by: Yu, Wenhan, et al.
Published: (2025)

SciTS: Scientific Time Series Understanding and Generation with LLMs
by: Wu, Wen, et al.
Published: (2025)

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
by: Makhov, Denis, et al.
Published: (2025)

SciAgent: Tool-augmented Language Models for Scientific Reasoning
by: Ma, Yubo, et al.
Published: (2024)

WildSci: Advancing Scientific Reasoning from In-the-Wild Literature
by: Liu, Tengxiao, et al.
Published: (2026)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
by: Li, Jianan, et al.
Published: (2026)

LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
by: Kabra, Sanchit, et al.
Published: (2026)

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
by: Huang, Songtao, et al.
Published: (2025)

Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
by: Li, Sha, et al.
Published: (2025)

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
by: Zheng, Tianshi, et al.
Published: (2026)

ViLaCD-R1: A Vision-Language Framework for Semantic Change Detection in Remote Sensing
by: Ma, Xingwei, et al.
Published: (2025)

RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design
by: Xu, Jiawei, et al.
Published: (2025)

Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing
by: Lin, Xinyi, et al.
Published: (2025)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
by: Lan, Yifan, et al.
Published: (2026)

MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
by: Chen, Guoxin, et al.
Published: (2025)

SciMDR: Advancing Scientific Multimodal Document Reasoning
by: Chen, Ziyu, et al.
Published: (2026)

CORAL: Concept Drift Representation Learning for Co-evolving Time-series
by: Xu, Kunpeng, et al.
Published: (2025)

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
by: Xue, Xiangyuan, et al.
Published: (2025)

SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data
by: Liu, Dianyu, et al.
Published: (2026)

Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning
by: Yin, Ming, et al.
Published: (2025)

SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs
by: Chen, Haotian, et al.
Published: (2025)

CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation
by: Huang, Dong, et al.
Published: (2023)

CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs
by: Du, Yongkang, et al.
Published: (2026)

CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning
by: He, Jinwei, et al.
Published: (2024)

DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature
by: Li, Dawei, et al.
Published: (2024)