Related papers: Table-as-Search: Formulate Long-Horizon Agentic In…
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such…
The desire and ability to seek new information strategically are fundamental to human learning but often overlooked in current language agent evaluation. We analyze a popular web shopping task designed to test language agents' ability to…
Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation…
Task planning for autonomous agents has typically been done using deep learning models and simulation-based reinforcement learning. This research proposes combining inductive learning techniques with goal-directed answer set programming to…
Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular form. Previous approaches demonstrated notable performance by…
Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on…
Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as…
The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However,…
Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource…
Recent studies have highlighted their proficiency in some simple tasks like writing and coding through various reasoning strategies. However, LLM agents still struggle with tasks that require comprehensive planning, a process that…
This research builds on work in anticipatory human-machine interaction, a subfield of human-machine interaction where machines can facilitate advantageous interactions by anticipating a user's future state. The aim of this research is to…
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain…
TAPS is a Topology-Aware intra-operator Parallelism strategy Searching algorithm that generates intra-operator parallelism strategies by considering both intra-node and inter-node bandwidth. Most of the existing auto-parallelism works use…
Agentic systems augment large language models with external tools and iterative decision making, enabling complex tasks such as deep research, function calling, and coding. However, their long and intricate execution traces make failure…
Tables are fundamental in domains such as finance, healthcare, and public administration, yet real-world table tasks often involve noise, structural heterogeneity, and semantic complexity--issues underexplored in existing research that…
In an era of rapidly advancing data-driven applications, there is a growing demand for data in both research and practice. Synthetic data have emerged as an alternative when no real data is available (e.g., due to privacy regulations).…
Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of linear sequence of actions with an end state that marks task…
Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web navigation tasks,…
Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external data sources. Existing strategies fall into two paradigms based on planning horizon: (1)…
Recent advancements in LLM-based information-seeking agents have achieved record-breaking performance on established benchmarks. However, these agents remain heavily reliant on search-engine-indexed knowledge, leaving a critical blind spot:…