Related papers: Skim: Speculative Execution for Fast and Efficient…
Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…
AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…
In this work, we propose and study optimal proactive resource allocation and demand shaping for data networks. Motivated by the recent findings on the predictability of human behavior patterns in data networks, and the emergence of highly…
The field of web and mobile software frameworks is relatively mature, with a large variety of tools in different languages that facilitate traditional app development where data in a relational database is displayed and modified. Our…
Software agents can be used to automate many of the tedious, time-consuming information processing tasks that humans currently have to complete manually. However, to do so, agent plans must be capable of representing the myriad of actions…
The current state of modern web interfaces, especially in regards to accessibility focused usage is extremely lacking. Traditional methods for web interaction, such as scripting languages and screen readers, often lack the flexibility to…
Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of…
We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts. The basic building…
We describe Swivel, a new compiler framework for hardening WebAssembly (Wasm) against Spectre attacks. Outside the browser, Wasm has become a popular lightweight, in-process sandbox and is, for example, used in production to isolate…
This paper studies the problem of multi-agent trajectory prediction in crowded unknown environments. A novel energy function optimization-based framework is proposed to generate prediction trajectories. Firstly, a new energy function is…
Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…
Semantic web technologies have shown their effectiveness, especially when it comes to knowledge representation, reasoning, and data integration. However, the original semantic web vision, whereby machine readable web data could be…
This work presents Drake, a dynamic executive for temporal plans with choice. Dynamic plan execution strategies allow an autonomous agent to react quickly to unfolding events, improving the robustness of the agent. Prior work developed…
Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security…
Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior…
LLM agents execute in an interleaved reasoning-and-action loop, where future tool calls cannot be launched until the current reasoning step completes. This serial dependency inflates end-to-end latency and leaves the model idle while…
Journalistic fact-checking, as well as social or economic research, require analyzing high-quality statistics datasets (SDs, in short). However, retrieving SD corpora at scale may be hard, inefficient, or impossible, depending on how they…
Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheaper local model is likely to fail. Existing LLM cascades usually route whole queries before execution, but task difficulty shifts…
Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…
The proliferation of GPS-enabled devices has led to the development of numerous location-based services. These services need to process massive amounts of spatial data in real-time. The current scale of spatial data cannot be handled using…