Related papers: Kimi K2.5: Visual Agentic Intelligence
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which improves upon Muon with a novel QK-clip technique to…
The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent…
We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base…
Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcement learning, and lack planning grounded in real…
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints,…
Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multi-agent systems can be useful for employing agents…
The rapid progress of Large Language Models has advanced agentic systems in decision-making, coordination, and task execution. Yet, existing agentic system generation frameworks lack full autonomy, missing from-scratch agent generation,…
Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Expansion (open-web search). However, existing evaluations fall…
We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagement with environments and tools. This…
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large…
This paper presents a Large Language Model (LLM) based conversational agent system designed to enhance human-machine collaboration in Machine Learning Operations (MLOps). We introduce the Swarm Agent, an extensible architecture that…
The automatic reading of text-intensive images represents a significant advancement toward achieving Artificial General Intelligence (AGI). In this paper we present KOSMOS-2.5, a multimodal literate model for machine reading of…
Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Building fully omni-capable models that can integrate text,…
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…
The integration of Large Language Models (LLMs) with specialized tools presents new opportunities for intelligent automation systems. However, orchestrating multiple LLM-driven agents to tackle complex tasks remains challenging due to…
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B…
Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless…
Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of…
Although LLMs demonstrate proficiency in several text-based reasoning and planning tasks, their implementation in robotics control is constrained by significant deficiencies: (1) LLM agents are designed to work mainly with textual inputs…
The Agentic Service Ecosystem consists of heterogeneous autonomous agents (e.g., intelligent machines, humans, and human-machine hybrid systems) that interact through resource exchange and service co-creation. These agents, with distinct…