arXiv AI
Understanding the Benefits of Scaffolds through Computational Separations
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 13
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
arXiv:2608. 12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods.
arXiv AI
Jul 28
Masked Distillation: Internalizing the Chain-of-Thought in Language Models
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
Hugging Face Trending Papers
Aug 12
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time.
arXiv Computation and Language
Sep 22
Harness-Zero: Harness Distillation via Agent-as-Harness
arXiv:2609.24974v1 Announce Type: cross Abstract: Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain...
arXiv Machine Learning
Oct 12
Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
arXiv:2605. 09724v2 Announce Type: replace Abstract: Existing accounts of grokking explain the phenomena in terms of mechanistic frameworks such as circuit efficiency or lazy-to-rich transitions.
arXiv AI
Oct 2
Masked Self-Distillation: Internalizing the Chain-of-Thought in Language Models
The paper introduces masked self‑distillation, a post‑training framework that trains a language model to internalize portions of its own intermediate reasoning traces. By varying the fraction of trace internalized, the authors demonstrate that models can achieve higher inference efficiency and improved task performance on math and graph‑coloring problems. Experiments on Qwen3‑4B and Qwen3‑8B show that the method generalizes well to in‑domain out‑of‑distribution cases without catastrophic forgetting, and that supervised fine‑tuning alone can reduce trace length at the expense of generalization.