AI Reasoning

AI Reasoning

AI System Scores Perfect 180 on the LSAT Exam

A new research paper demonstrates an AI system achieving a perfect score on the Law School Admission Test, showcasing dramatic advances in machine reasoning and logical analysis capabilities.

LLM Research

Surface Heuristics Override Deep Reasoning in LLMs

New research reveals LLMs rely on shallow surface-level patterns rather than true logical reasoning, with surface heuristics systematically overriding implicit constraints even in advanced models.

AI Research

Test-Time Compute: Three Techniques Making AI Think Longer

Modern AI models use test-time compute to improve responses through extended reasoning. Three key techniques—chain-of-thought, self-consistency, and reward-guided search—are reshaping how AI systems approach complex problems.

LLM Research

New Metric Measures LLM Reasoning Depth via Deep-Thinking Tokens

Researchers propose measuring LLM reasoning quality through 'deep-thinking tokens' rather than output length, offering new insights into how AI models actually process complex problems.

LLM Research

New Method Internalizes LLM Reasoning Through Latent Actions

Researchers propose a novel approach to improve LLM reasoning by discovering and replaying latent actions, potentially reducing inference costs while maintaining reasoning quality.

LLM Research

Knowledge Model Prompting Boosts LLM Planning Performance

New research introduces Knowledge Model Prompting, a technique that enhances LLM reasoning on complex planning tasks by structuring domain knowledge representation.

LLM Research

Policy of Thoughts: Evolving LLM Reasoning at Test Time

New research introduces test-time policy evolution to scale LLM reasoning without additional training, enabling models to dynamically improve their problem-solving strategies during inference.

LLM Research

Process-Supervised RL: Precise Error Penalization Boosts LLM Reas

New research introduces a method to preserve correct reasoning steps while penalizing errors, improving LLM performance through more nuanced reinforcement learning credit assignment.

LLM Research

Graph-Guided LLM Reasoning: Belief Propagation for Complex AI Inv

New research combines graph-based local reasoning with belief propagation to help LLMs tackle complex investigative tasks, enabling more reliable multi-step analysis in AI systems.

neuro-symbolic AI

Tensor Logic: Bridging Symbolic AI and Neural Networks

New research unifies Datalog symbolic reasoning with neural computation via tensor contractions, enabling differentiable logic programming with potential implications for AI reasoning systems.

neuro-symbolic AI

Tensor Networks Bridge Neural and Symbolic AI Reasoning

New research proposes tensor network mathematics to unify neural networks with symbolic AI, potentially enabling more interpretable and reasoning-capable AI systems.

LLM Research

How Similarity Retrieval Creates Reasoning Biases in LLMs

New research reveals how LLMs develop 'directional attractors' during reasoning tasks, showing that similarity-based retrieval mechanisms systematically steer iterative summarization toward predictable patterns.