Cover Image

Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Eo, Sugyeong, Moon, Hyeonseok, Zi, Evelyn Hayoon, Park, Chanjun, Lim, Heuiseok
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
by: Eo, Sugyeong, et al.
Published: (2026)

MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
by: Park, Chanhee, et al.
Published: (2025)

Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models
by: Moon, Hyeonseok, et al.
Published: (2024)

FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
by: Jung, Dahyun, et al.
Published: (2025)

Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning
by: Eo, Sugyeong, et al.
Published: (2025)

NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
by: Moon, Hyeonseok, et al.
Published: (2025)

Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline
by: Koo, Seonmin, et al.
Published: (2024)

ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
by: Park, Jeiyoon, et al.
Published: (2024)

Translation of Multifaceted Data without Re-Training of Machine Translation Systems
by: Moon, Hyeonseok, et al.
Published: (2024)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
by: Park, Jeiyoon, et al.
Published: (2024)

The Impact of Negated Text on Hallucination with Large Language Models
by: Seo, Jaehyung, et al.
Published: (2025)

Call for Rigor in Reporting Quality of Instruction Tuning Data
by: Moon, Hyeonseok, et al.
Published: (2025)

KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
by: Kim, Dongjun, et al.
Published: (2025)

Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer
by: Lee, Seungyoon, et al.
Published: (2025)

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
by: Yoon, Jeongho, et al.
Published: (2026)

Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
by: Kim, Dongjun, et al.
Published: (2025)

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
by: Shin, Joongmin, et al.
Published: (2026)

CoME: An Unlearning-based Approach to Conflict-free Model Editing
by: Jung, Dahyun, et al.
Published: (2025)

Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
by: Lee, Seungyoon, et al.
Published: (2024)

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
by: Jang, Youngjoon, et al.
Published: (2025)

LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model
by: Jang, Youngjoon, et al.
Published: (2026)

Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard
by: Park, Chanjun, et al.
Published: (2024)

TORSO: Template-Oriented Reasoning Towards General Tasks
by: Kim, Minhyuk, et al.
Published: (2025)

Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations
by: Jang, Yoonna, et al.
Published: (2024)

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
by: Zheng, Haizhong, et al.
Published: (2025)

M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
by: Shin, Joongmin, et al.
Published: (2026)

Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue
by: Park, Jeiyoon, et al.
Published: (2022)

InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasets
by: Kim, Yungi, et al.
Published: (2024)

Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
by: Jung, Dahyun, et al.
Published: (2026)

Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
by: Shim, Gyuho, et al.
Published: (2026)

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
by: Cheng, Sitao, et al.
Published: (2024)

Thought Communication in Multiagent Collaboration
by: Zheng, Yujia, et al.
Published: (2025)

Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoning
by: Ling, Zehui, et al.
Published: (2025)

CNN-based Multi-In-Multi-Out Model for Efficient Spatiotemporal Prediction
by: Jin, Hyeonseok
Published: (2026)

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
by: Shin, Joongmin, et al.
Published: (2026)

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
by: Chun, Yongchan, et al.
Published: (2026)

Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning
by: Chen, Xuhang, et al.
Published: (2025)

TS-Debate: Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
by: Trirat, Patara, et al.
Published: (2026)

ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction
by: Jung, Jeesu, et al.
Published: (2025)

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism
by: Park, Chanjun, et al.
Published: (2024)