method · first seen 13 Oct 2026
chain-of-thought compression
Techniques that shorten long reasoning traces in reasoning models to reduce token usage without hurting accuracy.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DoubtLess: Training-Free Contrastive Decoding for Efficient ReasoningPapers · 13 Oct 2026 · Minghao Luo, Liang Chen
- Learning to Reason Efficiently with Interventional Step CreditPapers · 19 Oct 2026 · Guanda Li, Xuefeng Bai, Yulong Chen, Zhiyong Wang, Kehai Chen, Min Zhang
- Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent CostPapers · 2 Nov 2026 · Anton Hristov
Latest sources
- Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent CostPapers · 2 Nov 2026 · Anton Hristov
- Learning to Reason Efficiently with Interventional Step CreditPapers · 19 Oct 2026 · Guanda Li, Xuefeng Bai, Yulong Chen, Zhiyong Wang, Kehai Chen, Min Zhang
- DoubtLess: Training-Free Contrastive Decoding for Efficient ReasoningPapers · 13 Oct 2026 · Minghao Luo, Liang Chen