Joint Consistency casts test-time aggregation as Ising-type energy minimization with pairwise LLM-judge interactions, subsuming voting methods and outperforming baselines across reasoning tasks.
Evolving deeper LLM thinking
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.
CogAlpha combines LLM reasoning with code-level evolutionary search to discover financial alphas that show higher predictive accuracy and generalization than prior methods on five stock datasets.
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
Reasoning Memory decomposes reasoning trajectories into 32 million subquestion-subroutine pairs and retrieves them via in-thought prompts to improve language model performance on math, science, and coding benchmarks by up to 19.2%.
ExComm adds cross-agent conflict detection and soft belief correction plus trajectory diversification to agentic test-time scaling, yielding 5-6% gains over baselines on AIME and GAIA benchmarks.
GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.
citing papers explorer
-
Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization
Joint Consistency casts test-time aggregation as Ising-type energy minimization with pairwise LLM-judge interactions, subsuming voting methods and outperforming baselines across reasoning tasks.
-
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.
-
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
CogAlpha combines LLM reasoning with code-level evolutionary search to discover financial alphas that show higher predictive accuracy and generalization than prior methods on five stock datasets.
-
SeLaR: Selective Latent Reasoning in Large Language Models
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
-
Procedural Knowledge at Scale Improves Reasoning
Reasoning Memory decomposes reasoning trajectories into 32 million subquestion-subroutine pairs and retrieves them via in-thought prompts to improve language model performance on math, science, and coding benchmarks by up to 19.2%.
-
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
ExComm adds cross-agent conflict detection and soft belief correction plus trajectory diversification to agentic test-time scaling, yielding 5-6% gains over baselines on AIME and GAIA benchmarks.
-
GEAR: Genetic AutoResearch for Agentic Code Evolution
GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.