# ASTER: Agentic Scaling with Tool-integrated Extended Reasoning

arXiv: https://arxiv.org/abs/2602.01204 · HTML: https://mlsanity.com/paper/2602.01204/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset](https://mlsanity.com/paper/2504.16891/) (2025)
- [Skywork Open Reasoner 1 Technical Report](https://mlsanity.com/paper/2505.22312/) (2025)
- [Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2504.13914/) (2025)
- [Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.01441/) (2025)
- [On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models](https://mlsanity.com/paper/2512.07783/) (2025)
- [rStar2-Agent: Agentic Reasoning Technical Report](https://mlsanity.com/paper/2508.20722/) (2025)
- [Understanding Tool-Integrated Reasoning](https://mlsanity.com/paper/2508.19201/) (2025)
- [Demystifying Reinforcement Learning in Agentic Reasoning](https://mlsanity.com/paper/2510.11701/) (2025)
- [OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique](https://mlsanity.com/paper/2507.09075/) (2025)

## Built on by (most cited first, 5 of 5)

- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [SkillMaster: Toward Autonomous Skill Mastery in LLM Agents](https://mlsanity.com/paper/2605.08693/) (2026)
- [Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning](https://mlsanity.com/paper/2605.06326/) (2026)
- [Teaching Language Models to Think in Code](https://mlsanity.com/paper/2605.07237/) (2026)
- [AgentOmnia: Scaling Agentic Models for Full-Scenario Applications](https://mlsanity.com/paper/2607.23124/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) has emerged as a dominant paradigm for eliciting long-horizon reasoning in Large Language Models (LLMs). However, scaling Tool-Integrated Reasoning (TIR) via RL remains challenging due to interaction collapse: a pathological state where models fail to sustain multi-turn tool usage, instead degenerating into heavy internal reasoning with only trivial, post-hoc code verification. We systematically study three questions: (i) how cold-start SFT induces an agentic, tool-using behavioral prior, (ii) how the interaction density of cold-start trajectories shapes exploration and downstream RL outcomes, and (iii) how the RL interaction budget affects learning dynamics and generalization under varying inference-time budgets. We then introduce ASTER (Agentic Scaling with Tool-integrated Extended Reasoning), a framework that circumvents this collapse through a targeted cold-start strategy prioritizing interaction-dense trajectories. We find that a small expert cold-start set of just 4K interaction-dense trajectories yields the strongest downstream performance, establishing a robust prior that enables superior exploration during extended RL training. Extensive evaluations demonstrate that ASTER-4B achieves state-of-the-art results on competitive mathematical benchmarks, reaching 90.0% on AIME 2025, surpassing leading frontier open-source models, including DeepSeek-V3.2-Exp.