Related papers: LHAW: Controllable Underspecification for Long-Hor…
Human activity recognition (HAR) has become a key component of intelligent systems for healthcare monitoring, assistive living, smart environments, and human-computer interaction. Although deep learning has substantially improved HAR…
Unmanned Aerial Vehicles (UAVs) offer significant potential in dynamic, perception-intensive tasks such as search and rescue and environmental monitoring; however, their effectiveness is severely restricted by conventional pre-planned…
Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed…
Long-horizon robotic manipulation tasks require executing multiple interdependent subtasks in strict sequence, where errors in detecting subtask completion can cascade into downstream failures. Existing Vision-Language-Action (VLA) models…
Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a step-wise paradigm that lacks a global perspective, which causes error accumulation over…
Multi-turn tool calling is essential for LLMs to function as autonomous agents, yet synthesizing the training data required for these capabilities remains a fundamental challenge. Existing synthetic data generation pipelines often produce…
Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over diverse long-horizon…
Congenital heart disease (CHD) presents complex, lifelong challenges often underrepresented in traditional clinical metrics. While unstructured narratives offer rich insights into patient and caregiver experiences, manual thematic analysis…
This paper addresses the problem of both actively searching and tracking multiple unknown dynamic objects in a known environment with multiple cooperative autonomous agents with partial observability. The tracking of a target ends when the…
Speculative decoding promises faster inference for large language models (LLMs), yet existing methods fail to generalize to real-world settings. Benchmarks typically assume short contexts (e.g., 2K tokens), whereas practical workloads…
Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack…
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across…
Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly…
Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training.…
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…
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…
Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…
Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow…
Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning extended time horizons. While learning-based Rolling Horizon Optimization~(RHO) has emerged as…
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.…