arXiv AI
Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 9
From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers
The paper introduces LLoCoT, a looped latent‑reasoning framework that replaces the traditional left‑to‑right generation of chain‑of‑thought tokens with iterative refinement of a compact latent workspace using a shared transformer. By jointly updating latent slots over a few iterations and sampling latent tokens in parallel, LLoCoT feeds these into an autoregressive decoder for answer generation. Experiments on HumanEval and MBPP show that LLoCoT matches or surpasses explicit‑CoT baselines while dramatically reducing reasoning latency and increasing throughput.
arXiv AI
5d ago
e1: Learning Adaptive Control of Reasoning Effort
arXiv:2510.27042v3 Announce Type: replace Abstract: Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users m...
arXiv AI
Jun 16
Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate
arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.
arXiv AI
Aug 11
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions
arXiv:2608. 07968v1 Announce Type: cross Abstract: Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time.
arXiv Computation and Language
5d ago
Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
arXiv:2603.00578v2 Announce Type: replace-cross Abstract: Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial...
arXiv Machine Learning
Aug 4
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
arXiv:2608. 02585v1 Announce Type: new Abstract: Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen.