Buchumschlag

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Jin, Can, Peng, Hongwu, Zhang, Qixin, Tang, Yujin, Metaxas, Dimitris N., Che, Tong
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
von: Jin, Can, et al.
Veröffentlicht: (2024)

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
von: Jin, Can, et al.
Veröffentlicht: (2026)

Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
von: Jin, Can, et al.
Veröffentlicht: (2025)

Two Heads Are Better Than One: Collaborative LLM Embodied Agents for Human-Robot Interaction
von: Rosser, Mitchell, et al.
Veröffentlicht: (2024)

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
von: Jin, Can, et al.
Veröffentlicht: (2025)

Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
von: Zeng, Hui, et al.
Veröffentlicht: (2024)

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
von: Li, Jiakang, et al.
Veröffentlicht: (2026)

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
von: Zhang, Jiazheng, et al.
Veröffentlicht: (2025)

Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing
von: Biagiola, Matteo, et al.
Veröffentlicht: (2023)

APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking
von: Jin, Can, et al.
Veröffentlicht: (2024)

Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
von: Dafnis, Konstantinos M., et al.
Veröffentlicht: (2025)

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
von: Jin, Can, et al.
Veröffentlicht: (2026)

Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment
von: Yang, Linyao, et al.
Veröffentlicht: (2024)

Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection
von: Ryser, Alain, et al.
Veröffentlicht: (2024)

Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
von: Su, Haoyang, et al.
Veröffentlicht: (2024)

M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
von: Zhou, Yang, et al.
Veröffentlicht: (2025)

Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
von: Peng, Xin, et al.
Veröffentlicht: (2026)

RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
von: Jin, Can, et al.
Veröffentlicht: (2025)

Two Heads are Better Than One: Team Teaching in the Information Age.
von: Jurena, Donna Phin, et al.
Veröffentlicht: (1997)

LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
von: Zhou, Yang, et al.
Veröffentlicht: (2025)

SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
von: Fang, Sen, et al.
Veröffentlicht: (2026)

Two Heads Are Better than One: Simulating Large Transformers with Small Ones
von: Yu, Hantao, et al.
Veröffentlicht: (2025)

Reinforcement Learning Teachers of Test Time Scaling
von: Cetin, Edoardo, et al.
Veröffentlicht: (2025)

Don't Squander Your Transition Year: Two Heads Are Better Than One
von: Trey Guinn, et al.
Veröffentlicht: (2025)

Two Is Better Than One: Rotations Scale LoRAs
von: Guo, Hongcan, et al.
Veröffentlicht: (2025)

SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
von: Sato, Makoto, et al.
Veröffentlicht: (2026)

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
von: Li, Jiazheng, et al.
Veröffentlicht: (2025)

Joint Decision-Making in Robot Teleoperation: When are Two Heads Better Than One?
von: Nguyen, Duc-An, et al.
Veröffentlicht: (2025)

Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
von: Gao, Hang, et al.
Veröffentlicht: (2026)

Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture
von: Fu, Tianhao, et al.
Veröffentlicht: (2025)

Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses
von: Kim, Sungnyun, et al.
Veröffentlicht: (2025)

RAC: Rectified Flow Auto Coder
von: Fang, Sen, et al.
Veröffentlicht: (2026)

Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors
von: Peng, Likai, et al.
Veröffentlicht: (2026)

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
von: Zhang, Guibin, et al.
Veröffentlicht: (2024)

Is One Head Better Than Two? Dual Leadership and Firm Performance During the COVID‐19 Crisis
von: Md Reiazul Haque, et al.
Veröffentlicht: (2024)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
von: Wang, Haozhe, et al.
Veröffentlicht: (2025)

Evidence Over Plans: Online Trajectory Verification for Skill Distillation
von: Zhou, Yang, et al.
Veröffentlicht: (2026)

Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning
von: Sobhani, Mahbub E, et al.
Veröffentlicht: (2025)

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
von: Hu, Zhiyuan, et al.
Veröffentlicht: (2026)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
von: Sareen, Kusha, et al.
Veröffentlicht: (2025)