相关论文: InSTA: Towards Internet-Scale Training For Agents

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…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

Web browsing agents powered by large language models (LLMs) have shown tremendous potential in automating complex web-based tasks. Existing approaches typically rely on large LLMs (e.g., GPT-4o) to explore web environments and generate…

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized…

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we…

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In…

To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement…

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic…

Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often…

LLMs can now act as autonomous agents that interact with digital environments and complete specific objectives (e.g., arranging an online meeting). However, accuracy is still far from satisfactory, partly due to a lack of large-scale,…

Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and…

The advancement of large language models (LLMs) has significantly accelerated the development of search agents capable of autonomously gathering information through multi-turn web interactions. Various benchmarks have been proposed to…

The capabilities of a single large language model (LLM) agent for solving a complex task are limited. Connecting multiple LLM agents to a network can effectively improve overall performance. However, building an LLM agent network (LAN)…

Data plays a fundamental role in training Large Language Models (LLMs). Efficient data management, particularly in formulating a well-suited training dataset, is significant for enhancing model performance and improving training efficiency…

Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…

State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies…

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…