10 posts found
A practical framework for building self-play curricula without mistaking reward hacking, forgetting, or correlated self-grading for genuine capability gains.
Highlights of AI News for August 24 - 30 2026
A practitioner's tour of how an agent turns a doubtful model into a decision: model-predictive control and why replanning every step is the robustness, CEM and random shooting as the planners world-model papers actually run, planning through a posterior instead of a point estimate, and expected free energy with the sign convention stated the right way round.
Calibrated confidence is a permission slip — this week we spend it. From PILCO's 17.5 seconds of robot experience to V-JEPA 2 planning zero-shot on a Franka arm, we trace how uncertainty becomes action. Then we look at the 2026 result that breaks the arc's own thesis: a world model can be locally well-calibrated and globally, confidently wrong.
Trends in ICLR 2026 RSI workshop - Self-Evolving Agents
Trends in ICLR 2026 RSI workshop - Self-Evolving Agents
Highlights of Trends in ICLR 2026 RSI workshop
How to filter for correctness, not just fluency
With LLMs, when self-play works and when it doesn't.
AI Tutorials - The trend of Self-Play