Related papers: A Multi-Agent Framework for Stateful Inference-Tim…

Extending the capabilities of Large Language Models (LLMs) with functions or tools for environment interaction has led to the emergence of the agent paradigm. In industry, training an LLM is not always feasible because of the scarcity of…

Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capability for continuous code optimization and multi-turn…

Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in complex tasks. In this paper, we introduce MALT (Multi-Agent LLM…

Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge…

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…

While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…

This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs), aiming for a more accurate assessment of their capabilities and limitations. We utilize a multi-agent system to…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from…

With the development of artificial intelligence (AI), large language models (LLM) are widely used in many fields. However, the reasoning ability of LLM is still very limited when it comes to mathematical reasoning. Mathematics plays an…

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex,…

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across…

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key…

Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other instances and lack task-level consistency across the selected…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Persistent memory is turning language-model-based agents from stateless participants in isolated interactions into state-bearing components of LLM-based multi-agent systems. As memory becomes durable, reloadable, and behavior-shaping across…

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code…