Related papers: Data-Dependent Goal Modeling for ML-Enabled Law En…
Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable behavior within a single inference. Multi-agent search…
The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…
The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service (DoS) risks, Automatic Exploit Generation (AEG) systems suffer from semantic blindness, and Large…
The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance…
Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…
Intelligent agent systems based on Large Language Models (LLMs) have shown great potential in real-world applications. However, existing agent frameworks still face critical limitations in task planning and execution, restricting their…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…
Recent advances in language models (LMs) have driven significant progress in various software engineering tasks. However, existing LMs still struggle with complex programming scenarios due to limitations in data quality, model architecture,…
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory.…
Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic…
The rapid progress in Generative AI and Agent technologies is profoundly transforming enterprise data management and analytics. Traditional database applications and system deployment are fundamentally impacted by AI-driven tools, such as…
Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search systems that iteratively interact with external knowledge…
Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…
Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and precise knowledge representation, such as…
The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but…
Underlying relationships among Multi-Agent Systems (MAS) in hazardous scenarios can be represented as Game-theoretic models. This paper proposes a new hierarchical network-based model called Game-theoretic Utility Tree (GUT), which…
Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…
As machine learning (ML) is more tightly woven into society, it is imperative that we better characterize ML's strengths and limitations if we are to employ it responsibly. Existing benchmark environments for ML, such as board and video…
Goal Recognition (GR) is the problem of recognizing an agent's objectives based on observed actions. Recent data-driven approaches for GR alleviate the need for costly, manually crafted domain models. However, these approaches can only…
Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight…