Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the presence, structure, or horizon of planning, these systems dramatically increase reasoning length, yielding inefficient token use without reliable accuracy gains. We argue efficient agentic reasoning benefits from decomposing decision-making into three system
Record details
Published: 21 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
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.
AOP-Wiki EMOD 3.0: Data Model Expansions and Content Evaluation Framework for Using Agentic AI to Improve Integration between AOPs and New Approach Methodologies (NAMs)
arXiv · 20 May 2026
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
arXiv · 22 May 2026
Governance by Construction for Generalist Agents
arXiv · 20 May 2026
Heterogeneous Multi-Agent Modeling for Measurement and Network Analysis of the Data Service Market
arXiv · 22 May 2026
One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
arXiv · 22 May 2026
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
arXiv · 19 May 2026
How to cite this record
ethics.ai (21 May 2026), “Efficient Agentic Reasoning Through Self-Regulated Simulative Planning,” evidence record 3930, https://ethics.ai/record/3930 (originally published by arXiv).
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.