CopT reverses CoT by eliciting a draft answer first then using continuous-embedding contrastive verification and on-policy thinking to reflect and correct, yielding up to 23% higher accuracy and 57% fewer tokens without training.
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks.
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative 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.
A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
PIPO adds closed-loop policy-improvement feedback to RL post-training so updates that raise measured performance are reinforced and those that drop it are suppressed.
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
citing papers explorer
-
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
CopT reverses CoT by eliciting a draft answer first then using continuous-embedding contrastive verification and on-policy thinking to reflect and correct, yielding up to 23% higher accuracy and 57% fewer tokens without training.
-
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.
-
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
-
Policy Improvement Reinforcement Learning
PIPO adds closed-loop policy-improvement feedback to RL post-training so updates that raise measured performance are reinforced and those that drop it are suppressed.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.