Related papers: SkyRL-Agent: Efficient RL Training for Multi-turn …

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to…

We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. ComputerRL features the API-GUI paradigm, which unifies programmatic API calls and direct GUI…

Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination…

Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…

Software engineering (SWE) has recently emerged as a crucial testbed for next-generation LLM agents, demanding inherent capabilities in two critical dimensions: sustained iterative problem-solving (e.g., >50 interaction rounds) and…

Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test…

Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers…

With the recent rapid advancement of Agentic Intelligence, agentic tool use in LLMs has become increasingly important. During multi-turn interactions between agents and users, the dynamic, uncertain, and stochastic nature of user demands…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap,…

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In particular, there are key…

Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of repeatedly sampling trajectories from scratch is…

With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and…

The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the…

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on…

This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via progressive RL training. Specifically, we…

Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…

Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage…

Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks,…

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for…