Related papers: SAAS: Self-Aware Reinforcement Learning for Over-S…

Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual…

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…

We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…

Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query…

Retrieval-Augmented Language Models (RALMs) represent a classic paradigm where models enhance generative capabilities using external knowledge retrieved via a specialized module. Recent advancements in Agent techniques enable Large Language…

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to master autonomous search for complex question answering. However, particularly within multi-turn search scenarios, this interaction introduces a critical challenge:…

Real-time search methods are suited for tasks in which the agent is interacting with an initially unknown environment in real time. In such simultaneous planning and learning problems, the agent has to select its actions in a limited amount…

Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving…

Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use. However, prevailing systems rely on monolithic agents that suffer from…

Controlling energy systems usually involves manually designed policies for decision-making, which can be complex and time-consuming to develop. This process requires interdisciplinary collaboration among multiple domain experts, resulting…

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…

Multi-step agentic retrieval systems based on large language models (LLMs) have demonstrated remarkable performance in complex information search tasks. However, these systems still face significant challenges in practical applications,…

With recent advances in frontier multimodal large language models (MLLMs) for data understanding and visual reasoning, the role of LLMs has evolved from passive LLM-as-an-interface to proactive LLM-as-a-judge, enabling deeper integration…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Large language model (LLM) agents have demonstrated strong capabilities across diverse domains, yet automated agent design remains a significant challenge. Current automated agent design approaches are often constrained by limited search…

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as context. However, retrieval becomes increasingly time-consuming as the knowledge databases…

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…

Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of…