相关论文: Kimi K2.5: Visual Agentic Intelligence

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the…

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…

Current vision-language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and language instructions for manipulation. However, their success rate…

Foundation models, including large language models (LLMs) and vision-language models (VLMs), have recently enabled novel approaches to robot autonomy and human-robot interfaces. In parallel, vision-language-action models (VLAs) or large…

Large Language Models (LLMs) and Visual Language Models (VLMs) are attracting increasing interest due to their improving performance and applications across various domains and tasks. However, LLMs and VLMs can produce erroneous results,…

As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibility, and fair comparison. Vision agents lack such…

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present…

Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their…

We introduce QiboAgent, a reference implementation designed to serve as a practitioner's guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development…

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…

The development of Generalist Virtual Agents (GVAs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive…

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides…

Existing mobile device control agents often perform poorly when solving complex tasks requiring long-horizon planning and precise operations, typically due to a lack of relevant task experience or unfamiliarity with skill execution. We…

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills,…

Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An…

With the recent emergence of revolutionary autonomous agentic systems, research community is witnessing a significant shift from traditional static, passive, and domain-specific AI agents toward more dynamic, proactive, and generalizable…

The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal…

The integration of Large Language Models (LLMs) with microscopic traffic simulation offers a promising path toward autonomous urban planning and intelligent transportation analysis. However, existing monolithic agent architectures often…

This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability…

We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture…