相关论文: WebOperator: Action-Aware Tree Search for Autonomo…

Despite the rapid progress, LLMs for sequential decision-making (i.e., LLM agents) still struggle to produce diverse outputs. This leads to insufficient exploration, convergence to sub-optimal solutions, and becoming stuck in loops. Such…

Large Language Models (LLMs) have empowered autonomous agents to handle complex web navigation tasks. While recent studies integrate tree search to enhance long-horizon reasoning, applying these algorithms in web navigation faces two…

Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional algorithm-driven NAS relies on carefully hand-crafted search spaces to ensure executability,…

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better…

While scaling test-time compute through trajectory-level sampling has significantly improved Graphical User Interface (GUI) agents, the lack of regressive ability prevents the reuse of partial successes and the recovery from early missteps.…

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate…

Large Language Models have excelled in remarkable reasoning capabilities with advanced prompting techniques, but they fall short on tasks that require exploration, strategic foresight, and sequential decision-making. Recent works propose to…

Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy,…

Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning step is not only constrained locally but also influenced by…

Safe autonomous exploration of unknown environments is an essential skill for mobile robots to effectively and adaptively perform environmental mapping for diverse critical tasks. Due to its simplicity, most existing exploration methods…

Large language model-based web agents have shown strong potential in automating web interactions through advanced reasoning and instruction following. While retrieval-based memory derived from historical trajectories enables these agents to…

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…

Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents…

Robust and persistent localisation is essential for ensuring the safe operation of autonomous vehicles. When operating in large and diverse urban driving environments, autonomous vehicles are frequently exposed to situations that violate…

The integration of autonomous vehicles into urban and highway environments necessitates the development of robust and adaptable behavior planning systems. This study presents an innovative approach to address this challenge by utilizing a…

Recent advances in large language models (LLMs) have enabled agentic systems for sequential decision-making. Such agents must perceive their environment, reason across multiple time steps, and take actions that optimize long-term…

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with…

Autonomous agents need to make decisions in a sequential manner, under partially observable environment, and in consideration of how other agents behave. In critical situations, such decisions need to be made in real time for example to…

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which…

Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where…