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.
Adaptthink: Reasoning models can learn when to think
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
ExpThink reduces average CoT response length by up to 77% while improving accuracy on math benchmarks via experience-guided reward shaping and difficulty-adaptive advantage in RL.
Introduces a modality-switching mechanism for LLMs on spatial reasoning tasks using a trustworthiness and complexity based metric, showing up to 42% performance improvement.
citing papers explorer
-
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
ExpThink reduces average CoT response length by up to 77% while improving accuracy on math benchmarks via experience-guided reward shaping and difficulty-adaptive advantage in RL.