mlsanityData to 14 Oct 2026

Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs

arXiv 2510.06750 ↗First posted 8 Oct 2025cs.CLcited by 0

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

Abstract (arXiv)

Large Reasoning Models (LRMs) excel in structured tasks by emulating deliberate human reasoning but often suffer from overthinking, degrading performance and wasting resources. One possible baseline is to deploy both LLM and LRM, then route input by predicting whether it requires reasoning and may cause overthinking. However, deploying multiple models can be costly or impractical. We propose a superposed deployment strategy with a lightweight, training-free regulation to optimize inference by switching one model on and off. Instead of routing, we selectively unlearn from LRM at inference, scaling down computation while preserving reasoning. By analyzing the cumulative energy of singular values, we identify optimal low-rank projections to adjust reasoning just right.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 20 of its 41 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

20 of 41 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Reasoning Models Can Be Effective Without Thinking14 Apr
  2. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  3. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  4. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  5. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  6. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks12 Feb
  7. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan

Other references · 13

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  6. 2025Qwen3-Omni Technical Reportcited by 497
  7. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  8. 2025Training Language Models to Reason Efficientlycited by 247
  9. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 117
  10. 2024Learning to Route LLMs with Confidence Tokenscited by 67
  11. 2024MoDeGPT: Modular Decomposition for Large Language Model Compressioncited by 48
  12. 2020TRP: Trained Rank Pruning for Efficient Deep Neural Networkscited by 32
1 more
  1. 2025Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalizationcited by 29

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
  2. 2025SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
  3. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  4. 2025Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment
  5. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
  6. 2026HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs
  7. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
  8. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities