Related papers: Endless Terminals: Scaling RL Environments for Ter…

Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution…

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes…

Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search, debugging or terminal execution. This architectural pattern keeps the…

LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is…

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating…

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a…

Large language models (LLMs) are evolving from conversational systems into strong reasoners for tasks such as Olympiad mathematics and competitive programming. While scaling parameters and test-time computation has driven progress, a key…

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A…

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based…

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…

The latest advancements in AI and deep learning have led to a breakthrough in large language model (LLM)-based agents such as GPT-4. However, many commercial conversational agent development tools are pipeline-based and have limitations in…

We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL system for any LLM or…

Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that…

Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry…

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build…

Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories. Existing approaches mitigate this…

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To…