While recent advancements in Large Language Model-based Multi-Agent (LLM-MA) systems have shown promise, significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose 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. 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 source code is available at https://github.com/sony/talkhier.
8 December 2023 in Environmental Science and Pollution Research
With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications. However, state-of-the-art offline RL algorithms perform suboptimally when confronted with limited data confined to specific regions within the state space. Performance degradation is attributed to the inability of offline RL algorithms to learn appropriate actions for rare or unseen observations. This paper proposes a heuristic rule-based regularization technique and adaptively refines the initial knowledge from heuristics to considerably boost performance in limited data with partially omitted states. The key insight is that the regularization term mitigates erroneous actions for sparse samples and unobserved states covered by domain knowledge. Empirical evaluations on standard offline RL datasets demonstrate a substantial average performance increase compared to ensemble of domain knowledge and existing offline RL algorithms operating on limited data.
Autism spectrum disorder (ASD) is a specific type of generalized developmental disorder characterized by social communication disorders and narrow, repetitive stereotypical behaviors. Augmented reality (AR) has gained considerable attention and research in the developmental intervention of autism with its combination of virtual and real characteristics. This paper systematically understands the characteristics of social disorders in autistic patients and the current effective intervention methods, and obtains the development enlightenment for effective intervention for autistic patients. Through the in-depth exploration of the definition and characteristics of augmented reality technology, the feature matching between augmented reality technology and autistic social communication disorder is analyzed in detail, and then the feasibility of application is obtained. Finally, based on the research examples of foreign augmented reality technology in the social disorders of autistic patients, the development enlightenment of future augmented reality technology in autistic patients with social disorders is summarized.