Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
C3ot: Generatingshorterchain-of-thoughtwithoutcompromisingeffectiveness.arXiv preprint
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
TrigReason matches large reasoning model accuracy on math and science benchmarks by delegating most steps to small models and intervening selectively on three triggers, cutting latency by 43.9% and cost by 73.3%.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
NCoTS treats chain-of-thought reasoning as a search problem and uses a dual-factor heuristic to find paths that are over 3.5% more accurate and 22% shorter on benchmarks.
Empirical sweep disentangles importance criterion, restructuring level, and compression budget in CoT distillation, revealing granularity governs criterion utility, domain-dependent restructuring effects, and that training compression overestimates inference savings.
CROP achieves 80.6% token reduction on GSM8K, LogiQA and BIG-Bench Hard with only nominal accuracy decline by regularizing automatic prompt optimization with response-length feedback.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
citing papers explorer
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
TrigReason matches large reasoning model accuracy on math and science benchmarks by delegating most steps to small models and intervening selectively on three triggers, cutting latency by 43.9% and cost by 73.3%.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
LightThinker++: From Reasoning Compression to Memory Management
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
-
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
NCoTS treats chain-of-thought reasoning as a search problem and uses a dual-factor heuristic to find paths that are over 3.5% more accurate and 22% shorter on benchmarks.
-
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Empirical sweep disentangles importance criterion, restructuring level, and compression budget in CoT distillation, revealing granularity governs criterion utility, domain-dependent restructuring effects, and that training compression overestimates inference savings.
-
CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization
CROP achieves 80.6% token reduction on GSM8K, LogiQA and BIG-Bench Hard with only nominal accuracy decline by regularizing automatic prompt optimization with response-length feedback.
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.