AI ethics evidence index Search
Source-linked daily record
Evidence record 4729 · automatically gathered

SOD: Step-wise On-policy Distillation for Small Language Model Agents

Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement learning methods like group relative policy optimization provide only sparse outcome-level rewards. Recently, on-policy distillation (OPD) has gained popularity by supplying dense token-level supervision from a teacher on student-generated trajectories. However, our experiments indicate that applying OPD to TIR leads t

Record details

Published: 8 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Children & education · Agents & autonomy
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Regulation · Shared topic: Children & education

Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning

arXiv · 28 June 2026

Shared topic: Regulation · Shared topic: Children & education

Large Language Models as a Semantic Interface and Ethical Mediator in Neuro-Digital Ecosystems: Conceptual Foundations and a Regulatory Imperative

arXiv · 18 March 2026

Shared topic: Regulation · Shared topic: Children & education

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

arXiv · 7 July 2026

Shared topic: Regulation · Shared topic: Children & education

Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation

HuggingFace Daily Papers · 14 July 2026

Shared topic: Regulation · Shared topic: Children & education

Multi-Turn On-Policy Distillation with Prefix Replay

HuggingFace Daily Papers · 15 July 2026

Shared topic: Regulation · Shared topic: Children & education

AutoSynthesis: An agentic system for automated meta-analysis

arXiv · 16 July 2026

How to cite this record

ethics.ai (8 May 2026), “SOD: Step-wise On-policy Distillation for Small Language Model Agents,” evidence record 4729, https://ethics.ai/record/4729 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.