Related papers: WebOperator: Action-Aware Tree Search for Autonomo…
Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…
This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language…
As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted…
We consider the neighborhood tree induced by alternating the use of different neighborhood structures within a local search descent. We investigate the issue of designing a search strategy operating at the neighborhood tree level by…
In the context of tree-search stochastic planning algorithms where a generative model is available, we consider on-line planning algorithms building trees in order to recommend an action. We investigate the question of avoiding re-planning…
LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…
Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…
We present TreeIRL, a novel planner for autonomous driving that combines Monte Carlo tree search (MCTS) and inverse reinforcement learning (IRL) to achieve state-of-the-art performance in simulation and in real-world driving. The core idea…
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Internet. While this integration enhances model capability, it…
In real practice, questions are typically complex and knowledge-intensive, requiring Large Language Models (LLMs) to recognize the multifaceted nature of the question and reason across multiple information sources. Iterative and adaptive…
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…
Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information…
We consider task and motion planning in complex dynamic environments for problems expressed in terms of a set of Linear Temporal Logic (LTL) constraints, and a reward function. We propose a methodology based on reinforcement learning that…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…
Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determine whether the agent successfully completed the tasks.…
Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. However, current agents struggle with repetitive errors and lack…
Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are…
Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources…
Effective information seeking in the vast and ever-growing digital landscape requires balancing expansive search with strategic reasoning. Current large language model (LLM)-based agents struggle to achieve this balance due to limitations…
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently…