Related papers: Efficient Dynamic Ensembling for Multiple LLM Expe…

The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive frameworks for dynamically changing environments. This paper introduces RL-Focal, a two-stage RL…

Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements in Large Reasoning…

Background/Context: Large Language Models (LLMs) demonstrate strong performance on low-dimensional software engineering optimization tasks ($\le$11 features) but consistently underperform on high-dimensional problems where Bayesian methods…

We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs). Our framework consists of two modules: PairRanker…

Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This…

The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of…

Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and…

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

We propose a hybrid architecture that integrates decision tree-based symbolic reasoning with the generative capabilities of large language models (LLMs) within a coordinated multi-agent framework. Unlike prior approaches that loosely couple…

This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench…

Large Language Models (LLMs) have shown remarkable capabilities across various natural language processing tasks but often struggle to excel uniformly in diverse or complex domains. We propose a novel ensemble method - Diverse Fingerprint…

Large language models (LLMs) face significant challenges in specialized domains like telecommunication (Telecom) due to technical complexity, specialized terminology, and rapidly evolving knowledge. Traditional methods, such as scaling…

Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques. However, their ability is still limited in solving complicated science…

Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple models. While multi-agent frameworks can…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group discussion framework to…

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…

Efficient data selection is crucial to accelerate the pretraining of language model (LMs). While various methods have been proposed to enhance data efficiency, limited research has addressed the inherent conflicts between these approaches…

Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…