Related papers: CoSTA$\ast$: Cost-Sensitive Toolpath Agent for Mul…

Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task,…

The study of multi-task learning has drawn great attention from the community. Despite the remarkable progress, the challenge of optimally learning different tasks simultaneously remains to be explored. Previous works attempt to modify the…

Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder…

Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even when related tasks share reusable structure. We introduce…

Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Motion-planning problems, such as manipulation in cluttered environments, often require a collision-free shortest path to be computed quickly given a roadmap graph. Typically, the computational cost of evaluating whether an edge of the…

Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face significant challenges, including high…

We introduce a Content-based Document Alignment approach (CDA), an efficient method to align multilingual web documents based on content in creating parallel training data for machine translation (MT) systems operating at the industrial…

The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a promising paradigm by identifying a highly informative…

LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of…

We present an incremental search algorithm, called Lifelong-GLS, which combines the vertex efficiency of Lifelong Planning A* (LPA*) and the edge efficiency of Generalized Lazy Search (GLS) for efficient replanning on dynamic graphs where…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpora. However, this paradigm has significant industrial…

This paper addresses a generalization problem of Multi-Agent Pathfinding (MAPF), called Collaborative Task Sequencing - Multi-Agent Pathfinding (CTS-MAPF), where agents must plan collision-free paths and visit a series of intermediate task…

The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal…

Object rearrangement planning in complex, cluttered environments is a common challenge in warehouses, households, and rescue sites. Prior studies largely address monotone instances, whereas real-world tasks are often non-monotone-objects…

Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time. Existing solutions have proposed coreset selection methods to improve data efficiency…

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…

Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To…