arXiv AI
More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 17
Continual Self-Improvement with Lightweight Experiential Latent Memories
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
arXiv AI
Jun 17
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
arXiv:2606. 17687v1 Announce Type: cross Abstract: Despite remarkable performance on complex tasks, Large Reasoning Models (LRMs) often generate excessively long Chain-of-Thoughts (CoT), inflating computational costs even for simple queries.
arXiv AI
Oct 15
e1: Learning Adaptive Control of Reasoning Effort
arXiv:2510.27042v3 Announce Type: replace Abstract: Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users m...
arXiv AI
Sep 28
Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
The paper demonstrates that fine‑tuning reasoning models to predict their own confidence at intermediate steps—using only 600 self‑supervised examples—substantially improves inference efficiency. Without adding any explicit stopping or length penalties, the models generate up to 25 % fewer tokens while maintaining accuracy on mathematical, scientific, and coding benchmarks across several architectures. The study finds that confidence supervision preserves the models’ high‑level reasoning structure rather than merely suppressing specific behaviors.
arXiv AI
Jul 7
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
arXiv:2510. 18814v4 Announce Type: replace-cross Abstract: Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training?
arXiv Machine Learning
Jun 19
ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models
arXiv:2606. 19919v1 Announce Type: new Abstract: Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost.