Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
The evolution of thought: Tracking llm overthinking via reasoning dynamics analysis
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
SliceGraph maps process isomers in multi-run CoT reasoning, finding that 85.5% of 954 problem-model cells show correct trajectories splitting into multiple process families with 76.6% of run pairs cross-family on average.
Dynamic Rollout Editing reduces overthinking in RL-trained LLMs by editing post-answer continuations in successful rollouts and preferring the edited versions within GRPO groups.
PUMA detects reasoning-level semantic redundancy to enable early exit in chains of thought, achieving 26.2% average token reduction across five LRMs and five benchmarks while preserving accuracy and CoT quality.
STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.
Conformal risk control with upper and lower thresholds lets LLMs adaptively stop reasoning while guaranteeing a maximum error rate and minimizing token use.
SLAT applies segment-level adaptive trimming in RL to reduce CoT reasoning length by 50% while maintaining competitive accuracy on benchmarks.
citing papers explorer
-
A First-Principles Theory of Slow Thinking and Active Perception
Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
-
SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning
SliceGraph maps process isomers in multi-run CoT reasoning, finding that 85.5% of 954 problem-model cells show correct trajectories splitting into multiple process families with 76.6% of run pairs cross-family on average.
-
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
Dynamic Rollout Editing reduces overthinking in RL-trained LLMs by editing post-answer continuations in successful rollouts and preferring the edited versions within GRPO groups.
-
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
PUMA detects reasoning-level semantic redundancy to enable early exit in chains of thought, achieving 26.2% average token reduction across five LRMs and five benchmarks while preserving accuracy and CoT quality.
-
STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.
-
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
Conformal risk control with upper and lower thresholds lets LLMs adaptively stop reasoning while guaranteeing a maximum error rate and minimizing token use.
-
SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
SLAT applies segment-level adaptive trimming in RL to reduce CoT reasoning length by 50% while maintaining competitive accuracy on benchmarks.
- Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking