Related papers: STT-Arena: A More Realistic Environment for Tool-U…

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…

Generating an abstraction of a dynamic domain that aligns with a given purpose remains a significant challenge given that the choice of such an abstraction can impact an agent's ability to plan, reason, and provide explanations effectively.…

We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development -- instead of perplexity…

Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal manipulation. Typically, existing methods mainly embed spatiotemporal knowledge into visual…

As large language models (LLMs) are widely deployed as domain-specific agents, many benchmarks have been proposed to evaluate their ability to follow instructions and make decisions in real-world scenarios. However, business scenarios often…

Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research…

Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing…

Concepts serve as fundamental abstractions that support human reasoning and categorization. However, it remains unclear whether large language models truly capture such conceptual structures or primarily rely on surface-level pattern…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

The growing capabilities of large language models (LLMs) in instruction-following and context-understanding lead to the era of agents with numerous applications. Among these, task planning agents have become especially prominent in…

What if artificial agents could not just communicate, but also evolve, adapt, and reshape their worlds in ways we cannot fully predict? With llm now powering multi-agent systems and social simulations, we are witnessing new possibilities…

Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…

Decision conferences are structured, collaborative meetings that bring together experts from various fields to address complex issues and reach a consensus on recommendations for future actions or policies. These conferences often rely on…

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world…

Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; yet, it remains challenging due to the large volume of perceptual information, much of which is…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive…

Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like…

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based…

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…