Related papers: FoldAct: Efficient and Stable Context Folding for …

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world…

Developing decision-making algorithms for highly automated driving systems remains challenging, since these systems have to operate safely in an open and complex environments. Reinforcement Learning (RL) approaches can learn comprehensive…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of…

Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most…

Large language models (LLMs) have significantly improved their reasoning and decision-making capabilities, as seen in methods like ReAct. However, despite its effectiveness in tackling complex tasks, ReAct faces two main challenges: losing…

Continuous action spaces in reinforcement learning (RL) are commonly defined as multidimensional intervals. While intervals usually reflect the action boundaries for tasks well, they can be challenging for learning because the typically…

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context…

Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking, each target token's effective context remains short. We introduce EXACT, a…

Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all…

While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through lifelong interaction. Existing attempts to bridge this gap…

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to master autonomous search for complex question answering. However, particularly within multi-turn search scenarios, this interaction introduces a critical challenge:…

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

Recent research highlights the potential of multimodal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The…

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for…