Related papers: EnvFactory: Scaling Tool-Use Agents via Executable…

A central challenge in reinforcement learning (RL) is its dependence on extensive real-world interaction data to learn task-specific policies. While recent work demonstrates that large language models (LLMs) can mitigate this limitation by…

The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs…

Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task. In contrast,…

Executing complex terminal tasks remains a significant challenge for open-weight LLMs, constrained by two fundamental limitations. First, high-fidelity, executable training environments are scarce: environments synthesized from real-world…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…

The rapid advancement of large language models (LLMs) has created a diverse landscape of models, each excelling at different tasks. This diversity drives researchers to employ multiple LLMs in practice, leaving behind valuable multi-LLM log…

Large Language Model-based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based agent, which generally entails achieving a desired goal from…

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines. Unlike conventional programs, their execution, i.e., trajectories, is inherently stochastic and…

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift. We…

Assistive agents should not only take actions on behalf of a human, but also step out of the way and cede control when there are important decisions to be made. However, current methods for building assistive agents, whether via mimicking…

Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with…

Large Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectories still hinders the development of stronger LLM agents.…

Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing…

LLM-based tool agents offer natural language interfaces, enabling users to seamlessly interact with computing services. While REST APIs are valuable resources for building such agents, they must first be transformed into AI-compatible…

Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…

Embodied systems, where generative autonomous agents engage with the physical world through integrated perception, cognition, action, and advanced reasoning powered by large language models (LLMs), hold immense potential for addressing…

Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a…