Related papers: K^2-Agent: Co-Evolving Know-What and Know-How for …

Hierarchical agents have the potential to solve sequential decision making tasks with greater sample efficiency than their non-hierarchical counterparts because hierarchical agents can break down tasks into sets of subtasks that only…

Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across diverse capabilities. However, existing planning approaches struggle to construct accurate symbolic representations and…

Mobile graphical user interface (GUI) agents are designed to automate everyday tasks on smartphones. Recent advances in large language models (LLMs) have significantly enhanced the capabilities of mobile GUI agents. However, most…

The complexity of modern bioinformatics analysis has created a critical gap between data generation and developing scientific insights. While large language models (LLMs) have shown promise in scientific reasoning, they remain fundamentally…

Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities,…

Large language models (LLMs) are increasingly deployed as autonomous agents for multi-turn decision-making tasks. However, current agents typically rely on fixed cognitive patterns: non-thinking models generate immediate responses, while…

Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by "Context Explosion", where the accumulation of long text…

We introduce PhysicalAgent, an agentic framework for robotic manipulation that integrates iterative reasoning, diffusion-based video generation, and closed-loop execution. Given a textual instruction, our method generates short video…

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…

We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier) to enable continual intelligence growth through self-supervised…

We present QuadAgent, a training-free agent system for agile quadrotor flight guided by vision-language inputs. Unlike prior end-to-end or serial agent approaches, QuadAgent decouples high-level reasoning from low-level control using an…

Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates…

Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the…

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

The Hierarchical Reasoning Model (HRM) has impressive reasoning abilities given its small size, but has only been applied to supervised, static, fully-observable problems. One of HRM's strengths is its ability to adapt its computational…

Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter,…

The ubiquity of mobile phones makes mobile GUI understanding an important task. Most previous works in this domain require human-created metadata of screens (e.g. View Hierarchy) during inference, which unfortunately is often not available…

External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to translate into effective real-world task execution. Our…