Related papers: Milestone-Guided Policy Learning for Long-Horizon …

Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior…

Large language models (LLMs) have demonstrated notable potential in conducting complex tasks and are increasingly utilized in various financial applications. However, high-quality sequential financial investment decision-making remains…

Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…

Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…

Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet existing memory benchmarks are largely dialogue-centric, while…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely…

Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with environments that provide rich feedback. However, prevailing outcome-driven…

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance…

Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes…

Sampling multiple responses is a common way to improve LLM output quality, but it comes at the cost of additional computation. The key challenge is deciding when to stop generating new samples to balance accuracy gains against efficiency.…

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient…

LLM-based agents have made significant advancements in interactive environments, such as mobile operations and web browsing, and other domains beyond computer using. Current multi-agent systems universally excel in performance, compared to…

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning…

Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO)…

Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet…

In this work, we address the challenging problem of long-horizon goal-reaching policy learning from non-expert, action-free observation data. Unlike fully labeled expert data, our data is more accessible and avoids the costly process of…