Microsoft's Phi-4-Reasoning-Vision-15B model challenges the trend of ever-larger AI models by demonstrating strong reasoning capabilities with a comparatively compact size. Trained on curated reasoning data, it aims to achieve performance without the massive compute costs associated with frontier models. The model supports multimodal tasks, combining text and image understanding, and offers flexible reasoning modes for different workloads. This research highlights the importance of data quality and training strategy, suggesting that smarter training techniques can be as impactful as simply increasing model size, particularly for AI agents and practical deployments.
In this tutorial, we build a hierarchical planner agent using an open-source instruct model. We design a structured multi-agent architecture comprising a planner agent, an executor agent, and an aggregator agent, where each component plays a specialized role in solving complex tasks. We use the planner agent to decompose high-level goals into actionable steps, the executor agent to execute those steps using reasoning or Python tool execution, and the aggregator agent to synthesize results into a coherent final response. By integrating tool usage, structured planning, and iterative execution, we create a fully autonomous agent system that demonstrates how modern AI agents reason, plan, and act in a scalable and modular manner.
ByteDance Research has released DAPO (Dynamic Sampling Policy Optimization), an open-source reinforcement learning system for LLMs, aiming to improve reasoning abilities and address reproducibility issues. DAPO includes innovations like Clip-Higher, Dynamic Sampling, Token-level Policy Gradient Loss, and Overlong Reward Shaping, achieving a score of 50 on the AIME 2024 benchmark with the Qwen2.5-32B model.
