Related papers: Skim: Speculative Execution for Fast and Efficient…
Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…
The nonliteral interpretation of a text is hard to be understood by machine models due to its high context-sensitivity and heavy usage of figurative language. In this study, inspired by human reading comprehension, we propose a novel,…
With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replacing traditional applications. However, such workflows are…
Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely…
TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and…
The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a dual-branch network, i.e., SkimFocusNet, working in a…
Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a…
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools used by attackers are becoming more and more automated and…
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,…
Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long…
Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation…
Modern database systems allow users to query or process unstructured text or document columns using LLM-powered functions. Users can express an operation in natural language (e.g., "identify if this review mentions billing issues"), with…
Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external…
We present a novel model for capturing the behavior of an agent exhibiting sunk-cost bias in a stochastic environment. Agents exhibiting sunk-cost bias take into account the effort they have already spent on an endeavor when they evaluate…
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as…