RL Post-Training for LLMs: From "RLHF" to Reasoning-First Agents
How reinforcement learning post-training evolved from RLHF to sophisticated reasoning-first agents in 2025.
Read more →Research Blog
Latest research and insights from Kiibo AI
Offline RL Reboot: Diffusion Planners, "Clean Slate" Baselines, and Offline-to-Online Bridging
How offline RL is experiencing a renaissance through diffusion models, standardized baselines, and practical offline-to-online transitions.
Read more →Preference-Based RL Meets Foundation Models: Multimodal Feedback Without Reward Engineering
How foundation models are transforming preference-based RL by serving as scalable feedback sources.
Read more →Safe, Robust, and Generalizable RL: Benchmarks and Methods Converge
The field is shifting from "can it solve the benchmark?" to "can it keep working when the world shifts?"
Read more →Multi-Agent RL in 2025: Coordination, Transfer, and Scientific/Industrial Optimization
Multi-agent RL has matured beyond emergence demos into practical tools for coordination.
Read more →