Related papers: AlignEvoSkill: Towards Knowledge-Aware and Task-Al…

Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval…

A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like "clever but clueless interns" in novel environments. This severely limits their practical utility. To…

Large language models (LLMs) are increasingly deployed as conversational tutors in STEM education, yet most systems still rely on a single LLM with a static retrieval-augmented generation (RAG) pipeline over course materials. This design…

External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to translate into effective real-world task execution. Our…

Training agents to act competently in complex 3D environments from high-dimensional visual information is challenging. Reinforcement learning is conventionally used to train such agents, but requires a carefully designed reward function,…

The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. However, a significant gap remains in assessing to what…

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental…

Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions. In this…

Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks, while the further evolvement is limited to the lack of high-quality training data. In addition, traditional training approaches rely too much on…

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks…

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

Large language models (LLMs) excel in various tasks but are primarily trained on text data, limiting their application scope. Expanding LLM capabilities to include vision-language understanding is vital, yet training them on multimodal data…

Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human…

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…

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…

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for…

Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding model competence). Current LLMs often conflate these…

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills…

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when…