Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs

• URL: http://arxiv.org/abs/2603.15051v1
• Date: Mon, 16 Mar 2026 10:06:05 GMT
• Title: Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
• Abstract summary: We introduce AdaAnchor, a latent reasoning framework that performs silent iterative computation by refining a set of latent anchor vectors attached to the input.<n>AdaAnchor with adaptive halting yields accuracy gains of up to 5% over fixed-step latent refinement while reducing average latent refinement steps by 48-60% under the same maximum-step budget.
• Score: 3.0215547730060206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Token-level Chain-of-Thought (CoT) prompting has become a standard way to elicit multi-step reasoning in large language models (LLMs), especially for mathematical word problems. However, generating long intermediate traces increases output length and inference cost, and can be inefficient when the model could arrive at the correct answer without extensive verbalization. This has motivated latent-space reasoning approaches that shift computation into hidden representations and only emit a final answer. Yet, many latent reasoning methods depend on a fixed number of latent refinement steps at inference, adding another hyperparameter that must be tuned across models and datasets to balance accuracy and efficiency. We introduce AdaAnchor, a latent reasoning framework that performs silent iterative computation by refining a set of latent anchor vectors attached to the input. AdaAnchor further incorporates an adaptive halting mechanism that monitors anchor stability across iterations and terminates refinement once the anchor dynamics converge, allocating fewer steps to easier instances while reserving additional refinement steps for harder ones under a shared maximum-step budget. Our empirical evaluation across three mathematical word-problem benchmarks shows that AdaAnchor with adaptive halting yields accuracy gains of up to 5% over fixed-step latent refinement while reducing average latent refinement steps by 48-60% under the same maximum-step budget. Compared to standard reasoning baselines, AdaAnchor achieves large reductions in generated tokens (92-93%) by moving computation into silent latent refinement, offering a different accuracy-efficiency trade-off with substantially lower output-token usage.

Related papers

• Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning [11.094089165730383]
  Batched ConThought Reinforcement is a minimalist, single-stage training paradigm that unlocks efficient reasoning.<n>We show that BCR reduces token usage by 15.8% to 62.6% while consistently maintaining or improving accuracy.<n>These results prove BCR practical, showing simple structural incentives unlock latent high-density reasoning in Large Language Models.
  arXiv  Detail & Related papers  (2026-04-02T17:58:50Z)
• Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning [66.22060690012512]
  Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy.<n>We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution.
  arXiv  Detail & Related papers  (2026-02-27T20:23:59Z)
• EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models [42.49934375597466]
  Large Reasoning Models (LRMs) excel at complex reasoning tasks through extended chain-of-thought generation.<n>We find that the entropy of the model's output distribution in early reasoning steps reliably distinguishes correct from incorrect reasoning.<n>We propose EntroCut, a training-free method that dynamically truncates reasoning by identifying high-confidence states.
  arXiv  Detail & Related papers  (2026-01-30T06:19:16Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• Arbitrage: Efficient Reasoning via Advantage-Aware Speculation [71.45710345765528]
  Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens.<n>But due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks.<n>We propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models.
  arXiv  Detail & Related papers  (2025-12-04T17:50:53Z)
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs [57.217593337454026]
  TokenSqueeze is a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data.<n>We show that TokenSqueeze reduces token usage while maintaining accuracy on the MATH500 benchmark.
  arXiv  Detail & Related papers  (2025-11-17T10:38:56Z)
• ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models [0.0]
  Reasoning Suppression (ARS) is a training-free approach that dynamically suppresses redundant reasoning steps.<n>ARS achieves up to 53%, 46.1%, and 57.9% in token, latency and energy reduction, while maintaining or improving accuracy.
  arXiv  Detail & Related papers  (2025-09-29T20:19:41Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching [64.74765550805024]
  Chain-of-Thought prompting elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs.<n>We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints.<n>SoT achieves token reductions of up to 84% with minimal accuracy loss across 18 reasoning datasets.
  arXiv  Detail & Related papers  (2025-03-07T06:57:17Z)

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.