Related papers: Do Agents Need to Plan Step-by-Step? Rethinking Pl…
Long-horizon AI agents execute complex workflows spanning hundreds of sequential actions, yet a single wrong assumption early on can cascade into irreversible errors. When instructions are incomplete, the agent must decide not only whether…
Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods struggle with complex, long-horizon tasks because they…
Long-horizon embodied planning underpins embodied AI. To accomplish long-horizon tasks, one of the most feasible ways is to decompose abstract instructions into a sequence of actionable steps. Foundation models still face logical errors and…
Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become stronger, the main bottleneck shifts from local skill execution to maintaining a coherent…
Many applications involving complex multi-task problems such as disaster relief, logistics and manufacturing necessitate the deployment and coordination of heterogeneous multi-agent systems due to the sheer number of tasks that must be…
Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…
Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether…
How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user's specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM's…
Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…
Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with…
ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a…
Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing…
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…
Open world language conditioned task planning is crucial for robots operating in large-scale household environments. While many recent works attempt to address this problem using Large Language Models (LLMs) via prompting or training, a key…
Efficient coordination and planning is essential for large-scale multi-agent systems that collaborate in a shared dynamic environment. Heuristic search methods or learning-based approaches often lack the guarantee on correctness and…
Lifelong Multi-Agent Path Finding (MAPF) is critical for modern warehouse automation, which requires multiple robots to continuously navigate conflict-free paths to optimize the overall system throughput. However, the complexity of…
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…
The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge…
We present a novel algorithm for large-scale Multi-Agent Path Finding (MAPF) that enables fast, scalable planning in dynamic environments such as automated warehouses. Our approach introduces finite-horizon hierarchical factorization, a…
Sequential decision-making and motion planning for robotic manipulation induce combinatorial complexity. For long-horizon tasks, especially when the environment comprises many objects that can be interacted with, planning efficiency becomes…