paper-with-me

홈 › Papers

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems

2025-02-16 · Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, Shingo Takamatsu

Recent advancements in LLM-based multi-agent (LLM-MA) systems have shown promise, yet significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose \textit{Talk Structurally, Act Hierarchically (TalkHier)}, a novel framework that introduces a structured communication protocol for context-rich exchanges and a hierarchical refinement system to address issues such as incorrect outputs, falsehoods, and biases. \textit{TalkHier} surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse), and majority voting strategies on current LLM and single-agent baselines (e.g., ReAct, GPT4o), across diverse tasks, including open-domain question answering, domain-specific selective questioning, and practical advertisement text generation. These results highlight its potential to set a new standard for LLM-MA systems, paving the way for more effective, adaptable, and collaborative multi-agent frameworks. The code is available https://github.com/sony/talkhier.

📄 PDF Abstract BibTeX arXiv:2502.11098

Code (1)

sony/talkhier 공식 구현

Tasks

Open-Domain Question AnsweringQuestion AnsweringText Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Disruptive Talk Detection in Multi-Party Dialogue within Collaborative Learning Environments with a Regularized User-Aware Network

2022-09-01 · SIGDIAL (ACL) 2022 9 · Kyungjin Park, Hyunwoo Sohn, Wookhee Min, Bradford Mott 외

Accurate detection and appropriate handling of disruptive talk in multi-party dialogue is essential for users to achieve shared goals. In collaborative game-based learning environments, detecting and attending to disrupt…

Talk in Pieces, See in Whole: Disentangled and Hierarchical Representation Learning in Language-based Object Detection

2025-09-29 · Sojung An, Kwanyong Park, Yong Jae Lee, Donghyun Kim arxiv

Vision-language models (VLMs) have advanced multimodal perception, demonstrated by open-vocabulary object detection with simple language queries. State-of-the-art VLMs still struggle to handle complex queries involving d…

Object Detection

VectorTalker: SVG Talking Face Generation with Progressive Vectorisation

2023-12-18 · Hao Hu, Xuan Wang, Jingxiang Sun, Yanbo Fan 외

High-fidelity and efficient audio-driven talking head generation has been a key research topic in computer graphics and computer vision. In this work, we study vector image based audio-driven talking head generation. Com…

Face GenerationImage ReconstructionTalking Face GenerationTalking Head Generation

LokiTalk: Learning Fine-Grained and Generalizable Correspondences to Enhance NeRF-based Talking Head Synthesis

2024-11-29 · Tianqi Li, Ruobing Zheng, Bonan Li, ZiCheng Zhang 외

Despite significant progress in talking head synthesis since the introduction of Neural Radiance Fields (NeRF), visual artifacts and high training costs persist as major obstacles to large-scale commercial adoption. We p…

NeRFTransfer Learning

Talking Detection In Collaborative Learning Environments

2021-10-14 · Wenjing Shi, Marios S. Pattichis, Sylvia Celedón-Pattichis, Carlos LópezLeiva

We study the problem of detecting talking activities in collaborative learning videos. Our approach uses head detection and projections of the log-magnitude of optical flow vectors to reduce the problem to a simple class…

Head DetectionOptical Flow Estimation