# When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation

arXiv: https://arxiv.org/abs/2610.12061 · HTML: https://mlsanity.com/paper/2610.12061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 28 of its 61 references that are in the map.
- First posted on arXiv 8 Oct 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, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning](https://mlsanity.com/paper/2505.11896/) (2025)
- [AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.08755/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2602.22817/) (2026)
- [Agentic Entropy-Balanced Policy Optimization](https://mlsanity.com/paper/2510.14545/) (2025)
- [OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis](https://mlsanity.com/paper/2603.20278/) (2026)
- [Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning](https://mlsanity.com/paper/2505.15154/) (2025)
- [Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.26684/) (2026)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning](https://mlsanity.com/paper/2509.23285/) (2025)
- [Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning](https://mlsanity.com/paper/2607.14171/) (2026)
- [Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents](https://mlsanity.com/paper/2603.07915/) (2026)
- [DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models](https://mlsanity.com/paper/2606.23181/) (2026)
- [Agent-Omit: Adaptive Context Omission for Efficient LLM Agents](https://mlsanity.com/paper/2602.04284/) (2026)
- [Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents](https://mlsanity.com/paper/2602.12662/) (2026)
- [Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization](https://mlsanity.com/paper/2602.22675/) (2026)
- [Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?](https://mlsanity.com/paper/2510.21007/) (2025)
- [ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning](https://mlsanity.com/paper/2603.06065/) (2026)

## Abstract (arXiv)

Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks. They typically perform reasoning before each action throughout an interaction trajectory. However, reasoning may not be necessary at every turn, as reasoning produced earlier can continue to support subsequent actions. A key challenge is therefore to determine when existing reasoning remains sufficient and when a new reasoning step is needed, without relying on costly generation-based verification. We find that decreases in the likelihood of subsequent reference actions after removing additional reasoning closely track whether those actions remain recoverable given earlier reasoning, providing an effective and lightweight signal for estimating cross-turn action support. Based on this observation, we propose Reasoning Adaptation through Cross-Turn Estimation (RACE), a training approach for adaptive agent reasoning. RACE introduces a Likelihood-Guided Progressive Reasoning Cover Detection (LoGiC) procedure that progressively identifies reasoning turns whose removal has limited impact on the current and subsequent reference actions. The resulting removal signals are incorporated into both supervised fine-tuning and agentic reinforcement learning, enabling the policy to learn when to reason and when to act directly. Extensive experiments on four representative agent benchmarks show that RACE substantially reduces reasoning cost while maintaining or improving task performance.