Related papers: PAFFA: Premeditated Actions For Fast Agents

Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a…

Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is…

Language Agent could be endowed with different mechanisms for autonomous task accomplishment. Current agents typically rely on fixed mechanisms or a set of mechanisms activated in a predefined order, limiting their adaptation to varied…

The growing capabilities of large language models (LLMs) in instruction-following and context-understanding lead to the era of agents with numerous applications. Among these, task planning agents have become especially prominent in…

While intelligent virtual assistants like Siri, Alexa, and Google Assistant have become ubiquitous in modern life, they still face limitations in their ability to follow multi-step instructions and accomplish complex goals articulated in…

The multi-agent pathfinding (MAPF) problem seeks collision-free paths for a team of agents from their current positions to their pre-set goals in a known environment, and is an essential problem found at the core of many logistics,…

AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an…

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused…

The popularity of Large Language Models (LLMs) have unleashed a new age ofLanguage Agents for solving a diverse range of tasks. While contemporary frontier LLMs are capable enough to power reasonably good Language agents, the closed-API…

Prescriptive Performance Analysis (PPA) has shown to be more useful than traditional descriptive and diagnostic analyses for making sense of Big Data (BD) frameworks' performance. In practice, when processing large (RDF) graphs on top of…

Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or…

This paper introduces Patched MOA (Mixture of Agents), an inference optimization technique that significantly enhances the performance of large language models (LLMs) across diverse software development tasks. We evaluate three inference…

Providing timely and actionable feedback is crucial for effective collaboration, learning, and coordination within teams. However, many teams face challenges in receiving feedback that aligns with their goals and promotes cohesion. We…

Modern consumer banking applications require accurate and efficient retrieval of information in response to user queries. Mapping user utterances to the most relevant Frequently Asked Questions (FAQs) is a crucial component of these…

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains…

We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key…

Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit…