Cover image

Eight Attempts, Four Routes, One Policy

TL;DR for operators A fixed budget of eight generated answers does not guarantee eight equally informative training experiences. Activation-Space Exploration (ASE), introduced by Zeng and colleagues,1 changes how those answers are generated by temporarily steering a model’s internal representations along directions learned from verified successes and failures. Against standard GRPO, ASE improves mathematical Mean@8 accuracy by 4.87 percentage points on Qwen3-1.7B and 1.87 points on Qwen3-8B, without increasing the eight-rollout training budget. Matched controls show that verifier-guided directions contribute beyond arbitrary steering. The intervention is used during training; the resulting model operates without it. ...

November 13, 2026 · 8 min · Zelina
Cover image

When Curiosity Becomes Contagious: Mutual Intrinsic Rewards in Multi-Agent RL

Doors are excellent teachers. A locked door in a maze looks trivial to a human observer. One agent opens it. Another agent walks through it. Everyone goes home, preferably before the training budget quietly evaporates. But for reinforcement-learning agents, especially in sparse-reward environments, that door is not a door. It is a credit-assignment trap wearing blue paint. ...

November 24, 2025 · 16 min · Zelina
Cover image

When Smart AI Gets It Wrong: Diagnosing the Knowing-Doing Gap in Language Model Agents

TL;DR for operators A smart agent can still be a bad decision-maker. That is the useful, slightly annoying lesson from LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities.1 The paper studies Gemma2 models acting in simple decision environments and finds that they often fail not because they cannot describe the right strategy, but because they do not reliably execute it. ...

April 23, 2025 · 17 min · Zelina