# Test-time Recursive Thinking: Self-Improvement without External Feedback

arXiv: https://arxiv.org/abs/2602.03094 · HTML: https://mlsanity.com/paper/2602.03094/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 25 of 25)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.07572/) (2025)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [ExGRPO: Learning to Reason from Experience](https://mlsanity.com/paper/2510.02245/) (2025)
- [Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models](https://mlsanity.com/paper/2509.26626/) (2025)
- [RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems](https://mlsanity.com/paper/2510.02263/) (2025)
- [Meta-RL Induces Exploration in Language Agents](https://mlsanity.com/paper/2512.16848/) (2025)
- [The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning](https://mlsanity.com/paper/2510.06557/) (2025)
- [The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute](https://mlsanity.com/paper/2511.02309/) (2025)
- [Human-AI Co-design for Clinical Prediction Models](https://mlsanity.com/paper/2601.09072/) (2026)
- [Scalable Oversight for Superhuman AI via Recursive Self-Critiquing](https://mlsanity.com/paper/2502.04675/) (2025)
- [MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning](https://mlsanity.com/paper/2510.10293/) (2025)

## Built on by (most cited first, 7 of 7)

- [Scaling Test-Time Compute for Agentic Coding](https://mlsanity.com/paper/2604.16529/) (2026)
- [Federation over Text: Insight Sharing for Multi-Agent Reasoning](https://mlsanity.com/paper/2604.16778/) (2026)
- [Test-Time Learning with an Evolving Library](https://mlsanity.com/paper/2605.14477/) (2026)
- [Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline](https://mlsanity.com/paper/2605.26132/) (2026)
- [Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images](https://mlsanity.com/paper/2604.11025/) (2026)
- [Agentic-imodels: Evolving agentic interpretability tools via autoresearch](https://mlsanity.com/paper/2605.03808/) (2026)
- [Register Tokens for Bounded-State Reasoning in Diffusion Language Models](https://mlsanity.com/paper/2609.16372/) (2026)

## Abstract (arXiv)

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for additional training. We identify two core challenges for such systems: (i) efficiently generating diverse, high-quality candidate solutions, and (ii) reliably selecting correct answers in the absence of ground-truth supervision. To address these challenges, we propose Test-time Recursive Thinking (TRT), an iterative self-improvement framework that conditions generation on rollout-specific strategies, accumulated knowledge, and self-generated verification signals. Using TRT, open-source models reach 100% accuracy on AIME-25/24, and on LiveCodeBench's most difficult problems, closed-source models improve by 10.4-14.8 percentage points without external feedback.