Related papers: ProgAgent:A Continual RL Agent with Progress-Aware…

Proactive task-oriented agents must autonomously anticipate user needs, identify actionable opportunities, and trigger software actions at appropriate moments - fundamentally shifting from reactive systems that await explicit instructions.…

Online lifelong learning enables agents to accumulate experience across interactions and continually improve on long-horizon tasks. However, existing methods typically treat retrieval from past experience as a passive operation, triggering…

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application…

We present PROGRESSOR, a novel framework that learns a task-agnostic reward function from videos, enabling policy training through goal-conditioned reinforcement learning (RL) without manual supervision. Underlying this reward is an…

Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice…

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

The application of advanced generative artificial intelligence in education is often constrained by the lack of real-time adaptability, personalization, and reliability of the content. To address these challenges, we propose ExpertAgent -…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain…

Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the…

LLM-based (Large Language Model) GUI (Graphical User Interface) agents can potentially reshape our daily lives significantly. However, current LLM-based GUI agents suffer from the scarcity of high-quality training data owing to the…

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…

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…

Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to…

Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such…

Image Restoration (IR) agents, leveraging multimodal large language models to perceive degradation and invoke restoration tools, have shown promise in automating IR tasks. However, existing IR agents typically lack an insight summarization…

We present ProgVLA, a compact vision-language-action (VLA) model designed for reliable robot manipulation under tight compute and memory budgets. The model specifically focuses on efficiently processing long multi-modal sequences by…

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…