Related papers: Skim: Speculative Execution for Fast and Efficient…
We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete…
Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200 data-extraction tasks across four common business and…
Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…
Training trustworthy agentic LLMs requires data that shows the grounded reasoning process, not just the final answer. Existing datasets fall short: question-answering data is outcome-only, chain-of-thought data is not tied to specific…
Modern AI assistants have made significant progress in natural language understanding and tool-use, with emerging efforts to interact with Web interfaces. However, current approaches that heavily rely on repeated LLM-driven HTML parsing are…
With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human…
While large language models have demonstrated impressive capabilities in web navigation tasks, the extensive context of web pages, often represented as DOM or Accessibility Tree (AxTree) structures, frequently exceeds model context limits.…
Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or additional predictors. However, in the decoding process of…
Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of…
Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…
Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different tasks. However, these knowledge types differ fundamentally: reasoning knowledge (e.g.,…
Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…
Symbolic execution is an effective path oriented and constraint based program analysis technique. Recently, there is a significant development in the research and application of symbolic execution. However, symbolic execution still suffers…
Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…
Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling…
CPU cache is a limited but crucial storage component in modern processors, whereas the cache timing side-channel may inadvertently leak information through the physically measurable timing variance. Speculative execution, an essential…
LLM-based agent applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs and latency due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context…
Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…
Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can lead to security vulnerabilities, as speculative instructions…
HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods reduce overall agent latency while maintaining performance. The main obstacle is the high…