On 6000 Qwen3-8B AIME traces, late-clustered moderate-to-severe backtracks are more common in incorrect outputs, enabling prefix-causal burst-aware filtering that outperforms fixed-length cutoffs at shallow and intermediate depths.
Answer convergence as a signal for early stopping in reasoning
4 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1
external citations · OpenAlex
years
2026 4verdicts
UNVERDICTED 4representative citing papers
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.
SAT reduces reasoning tokens by up to 40% across multiple large reasoning models and benchmarks by adaptively pruning steps based on difficulty while maintaining or improving accuracy.
citing papers explorer
-
The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
On 6000 Qwen3-8B AIME traces, late-clustered moderate-to-severe backtracks are more common in incorrect outputs, enabling prefix-causal burst-aware filtering that outperforms fixed-length cutoffs at shallow and intermediate depths.
-
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.
-
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
SAT reduces reasoning tokens by up to 40% across multiple large reasoning models and benchmarks by adaptively pruning steps based on difficulty while maintaining or improving accuracy.