SuperThoughts: Reasoning Tokens in Superposition

• URL: http://arxiv.org/abs/2606.13862v1
• Date: Thu, 11 Jun 2026 19:42:18 GMT
• Title: SuperThoughts: Reasoning Tokens in Superposition
• Abstract summary: Long Chain-of-Thought (CoT) reasoning improves problem-solving but is computationally expensive due to sequential token generation.<n>We propose SuperThoughts, which compresses pairs of consecutive CoT tokens into single latent representations.<n>SuperThoughts achieves $sim$20--30% CoT length reduction while maintaining accuracy with minimal degradation.
• Score: 26.164480068360362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation. While recent works explore reasoning in continuous latent spaces to bypass discrete token generation, they often struggle with training stability and fail to scale to complex, long-horizon tasks due to lack of supervision signal. We propose SuperThoughts, which compresses pairs of consecutive CoT tokens into single latent representations and decodes two tokens per step via a lightweight Multi-Token Prediction (MTP) module. This preserves discrete token supervision at training time while doubling throughput at inference time. We finetune Qwen2.5-Math-1.5B-Instruct, Qwen2.5-Math-7B-Instruct, Qwen2.5-Math-14B-Instruct, and evaluate on MATH500, AMC, OlympiadBench, and GPQA-Diamond. With a confidence-based adaptive mechanism that falls back to standard decoding when uncertain, SuperThoughts achieves $\sim$20--30\% CoT length reduction while maintaining accuracy with minimal degradation (1-2 points accuracy drop on most tasks).

Related papers

• Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective [7.155337546555976]
  We show how pause tokens reshape the training dynamics of fine-tuning.<n>Masked Boundary Pause consistently improves reasoning, achieving gains of up to 6 points on math and 2.5 points on code.<n>These results recast pause tokens as a training-dynamics intervention on the retention-adaptation trade-off.
  arXiv  Detail & Related papers  (2026-09-03T21:23:04Z)
• Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs [19.38885798529711]
  We propose textbfPair-In, Pair-Out (PIPO), which unifies both sides by viewing a latent compressor and an MTP head as mirror-image operations.<n>PIPO trains a lightweight confidence head that decides whether draft tokens should be accepted.<n>Experiments on AIME 2025, GPQA-Diamond, LiveCodeBench v6, and LongBench v2 with Qwen3.5-4B and 9B backbones show that PIPO improves pass@4 over regular decoding by up to $+7.15$ points.
  arXiv  Detail & Related papers  (2026-05-26T16:31:45Z)
• AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth [23.442686851761298]
  AdaPonderLM is a self-supervised recurrent language model that learns token-wise early exiting during pretraining.<n>AdaPonderLM reduces inference compute at about 10% while maintaining comparable language modeling perplexity and competitive downstream accuracy.
  arXiv  Detail & Related papers  (2026-03-02T14:28:16Z)
• Latent Reasoning with Supervised Thinking States [60.09942890192309]
  Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs.<n>We propose Thinking States, a method that performs reasoning em while the input is processing.<n>We show Thinking States leads to stronger reasoning behavior than CoT, successfully extrapolating to longer sequences than seen during training.
  arXiv  Detail & Related papers  (2026-02-09T07:12:41Z)
• Residual Context Diffusion Language Models [90.07635240595926]
  Residual Context Diffusion (RCD) is a module that converts discarded token representations into contextual residuals and injects them back for the next denoising step.<n>RCD consistently improves frontier dLLMs by 5-10 points in accuracy with minimal extra computation overhead.
  arXiv  Detail & Related papers  (2026-01-30T13:16:32Z)
• Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge [87.51901436392427]
  Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT)<n>Humans, by contrast, often reason softly by maintaining a tractable probability distribution over plausible next steps.<n>We propose Multiplex Thinking, a soft reasoning mechanism that samples K candidate tokens and aggregates their embeddings into a single continuous multiplex token.<n>Multiplex Thinking is self-adaptive: when the model is confident, the multiplex token is nearly discrete and behaves like standard CoT.
  arXiv  Detail & Related papers  (2026-01-13T18:48:00Z)
• Rethinking Thinking Tokens: LLMs as Improvement Operators [80.12087211785949]
  Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which allows them to explore solution strategies with self-checking.<n>This results in higher accuracy, but inflates context length, token/compute cost, and answer latency.<n>We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier?<n>We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace
  arXiv  Detail & Related papers  (2025-10-01T17:08:59Z)
• MARCOS: Deep Thinking by Markov Chain of Continuous Thoughts [82.46857666702924]
  We present a new paradigm for reasoning in large language models (LLMs)<n>Instead of autoregressively generating tokens, we model reasoning as a hidden Markov chain of continuous, high-dimensional "thoughts"<n>For the first time, MARCOS achieves performance comparable to token-based CoT, even surpassing it by 4.7% on GSM8K with up to 15.7x speedup in inference.
  arXiv  Detail & Related papers  (2025-09-29T16:44:22Z)
• Soft Tokens, Hard Truths [17.640897774014707]
  This work introduces a scalable method to learn continuous CoTs via reinforcement learning (RL)<n>We use "soft" tokens: mixtures of tokens together with noise on the input embedding to provide RL exploration.<n>On math reasoning benchmarks with Llama and Qwen models up to 8B, training with continuous CoTs match discrete-token CoTs for pass@1 and surpass them for pass@32.
  arXiv  Detail & Related papers  (2025-09-23T15:43:47Z)
• Multipole Attention for Efficient Long Context Reasoning [64.94673641704289]
  Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks.<n>LRMs need to generate long chain-of-thought reasoning in order to think before answering.<n>We introduce Multipole Attention, which accelerates autoregressive reasoning by only computing exact attention for the most important tokens.
  arXiv  Detail & Related papers  (2025-06-16T03:00:40Z)
• Fast Quiet-STaR: Thinking Without Thought Tokens [51.79231070632772]
  Fast Quiet STaR is a more efficient reasoning framework that preserves the benefits of token-level reasoning while reducing computational cost.<n>Our method introduces a curriculum learning based training strategy that gradually reduces the number of thought tokens.<n>Experiments on four benchmark datasets with Mistral 7B and Qwen2.5 7B demonstrate that Fast Quiet-STaR consistently outperforms Quiet-STaR in terms of average accuracy.
  arXiv  Detail & Related papers  (2025-05-23T11:14:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.