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

Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic simulations, machine learning, and workflow design, as well as iterative active learning…

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in multi-turn,…

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance…

Simulated environments have proven invaluable in Autonomous Cyber Operations (ACO) where Reinforcement Learning (RL) agents can be trained without the computational overhead of emulation. These environments must accurately represent…

We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quantitative, computation-intensive domains. Given only a dataset and a natural-language…

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…

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…

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior…

Large language model (LLM) agents have shown impressive reasoning capabilities in interactive decision-making tasks. These agents interact with environment through intermediate interfaces, such as predefined action spaces and interaction…

Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been limited to semi-automated environment synthesis or tasks…

Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in…

Recent SOTA approaches for embodied learning via interaction directly employ large language models (LLMs) as agents to determine the next steps in an environment. Due to their world knowledge and reasoning capabilities, LLM agents achieve…

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…

While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans,…

While Language Models (LMs) have made significant progress in automating machine learning engineering (MLE), the acquisition of high-quality MLE training data is significantly constrained. Current MLE benchmarks suffer from low scalability…

Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging…

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains…

Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…