Related papers: BrowseMaster: Towards Scalable Web Browsing via To…
High-dimensional decision-making tasks, such as business partner selection, involve evaluating large candidate pools with heterogeneous numerical, categorical, and textual features. While large language models (LLMs) offer strong in-context…
The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…
Spreadsheets are ubiquitous across the World Wide Web, playing a critical role in enhancing work efficiency across various domains. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not…
Explicit information seeking is essential to human problem-solving in practical environments characterized by incomplete information and noisy dynamics. When the true environmental state is not directly observable, humans seek information…
AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart…
Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments…
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…
Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…
Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA…
The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…
Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…
Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inherent limitations of LLMs in handling long text, current…
With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their failure to learn from the accumulated interaction history,…
Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and…
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…
The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in…
As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a…
Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into…
Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle…
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…