Related papers: Hybrid-Gym: Training Coding Agents to Generalize A…
Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live commercial Web APIs…
Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widely used for training generative robot policies. Despite its empirical success, the…
Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or…
Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We…
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…
Pre-training produces representations that are effective for a wide range of downstream tasks, but it is still unclear what properties of pre-training are necessary for effective gains. Notably, recent work shows that even pre-training on…
Foundation models (e.g., CodeBERT, GraphCodeBERT, CodeT5) work well for many software engineering tasks. These models are pre-trained (using self-supervision) with billions of code tokens, and then fine-tuned with hundreds of thousands of…
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially…
Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its…
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…
Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training. We introduce MetaLint, a meta-learning framework that…
Traditional approaches to training agents have generally involved a single, deterministic environment of minimal complexity to solve various tasks such as robot locomotion or computer vision. However, agents trained in static environments…
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…
Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…
Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where…
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…
The rise of embodied AI has greatly improved the possibility of general mobile agent systems. At present, many evaluation platforms with rich scenes, high visual fidelity and various application scenarios have been developed. In this paper,…
Many AI researchers are today striving to build agent teams for complex, dynamic multi-agent domains, with intended applications in arenas such as education, training, entertainment, information integration, and collective robotics.…
In multi-agent reinforcement learning (MARL), achieving multi-task generalization to diverse agents and objectives presents significant challenges. Existing online MARL algorithms primarily focus on single-task performance, but their lack…