VPG-EA applies variational posterior guidance and efficiency-aware distillation to compress LLM reasoning chains while preserving performance.
Adaptthink: Reasoning models can learn when to think
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
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.
CODA uses rollout-based difficulty signals to drive two gates that penalize verbosity on easy instances and promote deliberation on hard ones, cutting token use over 60% on simple tasks while maintaining accuracy.
citing papers explorer
-
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
VPG-EA applies variational posterior guidance and efficiency-aware distillation to compress LLM reasoning chains while preserving performance.
-
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.
-
CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning
CODA uses rollout-based difficulty signals to drive two gates that penalize verbosity on easy instances and promote deliberation on hard ones, cutting token use over 60% on simple tasks while maintaining accuracy.