mlsanityData to 7 Oct 2026

AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback

arXiv 2602.03084 ↗First posted 3 Feb 2026cs.CLcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large Language Models (LLMs) have achieved significant success in complex reasoning but remain bottlenecked by reliance on expert-annotated data and external verifiers. While existing self-evolution paradigms aim to bypass these constraints, they often fail to identify the optimal learning zone and risk reinforcing collective hallucinations and incorrect priors through flawed internal feedback. To address these challenges, we propose underlineAutonomous underlineEvolutionary underlineReasoning underlineOptimization (AERO), an unsupervised framework that achieves autonomous reasoning evolution by internalizing self-questioning, answering, and criticism within a synergistic dual-loop system. Inspired by the textitZone of Proximal Development (ZPD) theory, AERO utilizes entropy-based positioning to target the ``solvability gap'' and employs Independent Counterfactual Correction for robust verification. Furthermore, we introduce a Staggered Training Strategy to synchronize capability growth across functional roles and prevent curriculum collapse. Extensive evaluations across nine benchmarks spanning three domains demonstrate that AERO achieves average performance improvements of 4.57% on Qwen3-4B-Base and 5.10% on Qwen3-8B-Base, outperforming competitive baselines. Code is available at https://github.com/mira-ai-lab/AERO.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 37 of its 48 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

37 of 48 references.

References · 37

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  6. 2024Qwen2.5 Technical Reportcited by 4,713
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  8. 2024OpenAI o1 System Cardcited by 1,220
  9. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 988
  10. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  11. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 398
  12. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
25 more
  1. 2024KTO: Model Alignment as Prospect Theoretic Optimizationcited by 256
  2. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  3. 2025UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learningcited by 166
  4. 2017Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Playcited by 139
  5. 2025Maximizing Confidence Alone Improves Reasoningcited by 97
  6. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  7. 2025RLPR: Extrapolating RLVR to General Domains without Verifierscited by 83
  8. 2025Reinforcing General Reasoning without Verifierscited by 76
  9. 2025SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplinescited by 67
  10. 2025On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Modelscited by 64
  11. 2025PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Modelscited by 57
  12. 2025Language Self-Play For Data-Free Trainingcited by 42
  13. 2025VisPlay: Self-Evolving Vision-Language Models from Imagescited by 42
  14. 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoningcited by 40
  15. 2025Understanding Tool-Integrated Reasoningcited by 38
  16. 2025Generalist Reward Models: Found Inside Large Language Modelscited by 34
  17. 2025Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolutioncited by 24
  18. 2025NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learningcited by 15
  19. 2025R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learningcited by 15
  20. 2025Bootstrapping Task Spaces for Self-Improvementcited by 10
  21. 2025FormaRL: Enhancing Autoformalization with no Labeled Datacited by 9
  22. 2025PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problemscited by 7
  23. 2025Escaping the Verifier: Learning to Reason via Demonstrationscited by 7
  24. 2025SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Modelscited by 7
  25. 2025Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligencecited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training
  2. 2026On the Generalization Gap in Self-Evolving Language Model Reasoning
  3. 2026Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
  4. 2026When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning
  5. 2026Improving reasoning at inference time via uncertainty minimisation
  6. 2025From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models
  7. 2026Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
  8. 2026Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces