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.
R1-compress: Long chain-of-thought compression via chunk compression and search
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Entropy-guided supertokens from BPE on reasoning traces compress LLM outputs by 8.1% on average across models and math benchmarks with no accuracy loss while exposing strategy differences between correct and incorrect traces.
CRISP compresses chain-of-thought by 50-60% using intrinsic attention saliency from the termination token to prune redundancy while preserving accuracy on math tasks.
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
The paper delivers a unified survey of token economics for LLM agents, conceptualizing tokens as production factors, exchange mediums, and units of account across micro, meso, macro, and security dimensions using established economic theories.
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.
-
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Entropy-guided supertokens from BPE on reasoning traces compress LLM outputs by 8.1% on average across models and math benchmarks with no accuracy loss while exposing strategy differences between correct and incorrect traces.
-
CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning
CRISP compresses chain-of-thought by 50-60% using intrinsic attention saliency from the termination token to prune redundancy while preserving accuracy on math tasks.
-
MEMENTO: Teaching LLMs to Manage Their Own Context
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.
-
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.
-
Token Economics for LLM Agents: A Dual-View Study from Computing and Economics
The paper delivers a unified survey of token economics for LLM agents, conceptualizing tokens as production factors, exchange mediums, and units of account across micro, meso, macro, and security dimensions using established economic theories.
- Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration