Seonglae ChoOptimal Reasoning Length, AI Overthinking
Chain-of-Thought (CoT) length is not a case of "longer is better," but rather follows an inverted U-curve where accuracy initially increases but then decreases after a certain length. This indicates there is an optimal length.
If it's too short (underthinking), complex aspects can't be properly decomposed; if too long (overthinking), cumulative errors increase and performance drops.
During RL training (e.g., GRPO, PPO), the average CoT length naturally converges toward becoming shorter → the reward maximization process finds the optimal length, revealing a simplicity bias.
Manifold Steering Manifold_SteeringAries-iai • Updated 2025 Dec 3 9:40
Manifold_Steering
Aries-iai • Updated 2025 Dec 3 9:40
LLM overthinking exists in a low-dimensional manifold of the activation space, and by aligning and intervening along it. tokens can be significantly reduced while maintaining accuracy. Manifold Steering: Estimate the low-dimensional subspace of reasoning activations using PCA, and steer only along it. Overthinking is not a single direction but a phenomenon bound to a low-dimensional manifold. Results: Token reduction of up to ~71% across math, code, and QA tasks, with accuracy maintained or slightly improved.