Related papers: When Robots Do the Chores: A Benchmark and Agent f…
Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for…
Complex activities in real-world audio unfold over extended durations and exhibit hierarchical structure, yet most prior work focuses on short clips and isolated events. To bridge this gap, we introduce MultiAct, a new dataset and benchmark…
Long-tailed data distributions pose challenges for a variety of domains like e-commerce, finance, biomedical science, and cyber security, where the performance of machine learning models is often dominated by head categories while tail…
Completing Long-Horizon (LH) tasks in open-ended worlds is an important yet difficult problem for embodied agents. Existing approaches suffer from two key challenges: (1) they heavily rely on experiences obtained from human-created data or…
Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experience. In ultra-long video settings, relevant information is…
Although large language models (LLMs) have advanced rapidly, robust automation of complex software workflows remains an open problem. In long-horizon settings, agents frequently suffer from cascading errors and environmental stochasticity;…
Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…
The test-time compute strategy, such as Chain-of-Thought (CoT), has significantly enhanced the ability of large language models to solve complex tasks like logical reasoning. However, empirical studies indicate that simply increasing the…
Large language models (LLMs) have brought autonomous agents closer to artificial general intelligence (AGI) due to their promising generalization and emergent capabilities. There is, however, a lack of studies on how LLM-based agents…
While Large Language Models (LLMs) can exhibit impressive proficiency in isolated, short-term tasks, they often fail to maintain coherent performance over longer time horizons. In this paper, we present Vending-Bench, a simulated…
Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…
LLM-driven agents, particularly those using general frameworks like ReAct or human-inspired role-playing, often struggle in specialized domains that necessitate rigorously structured workflows. Fields such as remote sensing, requiring…
AI agents need to plan to achieve complex goals that involve orchestrating perception, sub-goal decomposition, and execution. These plans consist of ordered steps structured according to a Temporal Execution Order (TEO, a directed acyclic…
Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video…
We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates…
Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive load and streamline workflows. However, existing datasets suffer from two…
Bimanual robotic manipulation provides significant versatility, but also presents an inherent challenge due to the complexity involved in the spatial and temporal coordination between two hands. Existing works predominantly focus on…
Modern work relies on an assortment of digital collaboration tools, yet routine processes continue to suffer from human error and delay. To address this gap, this dissertation extends TheAgentCompany with a finance-focused environment and…
Bimanual manipulation, i.e., the coordinated use of two robotic arms to complete tasks, is essential for achieving human-level dexterity in robotics. Recent simulation benchmarks, e.g., RoboTwin and RLBench2, have advanced data-driven…