DART is a training-free router that accepts direct answers on draft agreement and allocates thinking budgets via draft entropy on disagreement, reporting accuracy gains and token reductions on math and code benchmarks across model scales.
Reasoning on a budget: A survey of adaptive and controllable test-time compute in llms
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
Consequence-aware scheduler using an issue-text predictor routes more compute to high-cost failures and cuts cost-weighted loss by 22-33% versus difficulty-based allocation on SWE-bench tasks.
ICR creates a virtual shorter distribution from shortest correct on-policy responses to regularize RL post-training toward concise yet accurate reasoning, improving the accuracy-length Pareto frontier on math and knowledge benchmarks.
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
citing papers explorer
-
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
DART is a training-free router that accepts direct answers on draft agreement and allocates thinking budgets via draft entropy on disagreement, reporting accuracy gains and token reductions on math and code benchmarks across model scales.
-
Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation
Consequence-aware scheduler using an issue-text predictor routes more compute to high-cost failures and cuts cost-weighted loss by 22-33% versus difficulty-based allocation on SWE-bench tasks.
-
Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
ICR creates a virtual shorter distribution from shortest correct on-policy responses to regularize RL post-training toward concise yet accurate reasoning, improving the accuracy-length Pareto frontier on math and knowledge benchmarks.
-
Stream-T1: Test-Time Scaling for Streaming Video Generation
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.