Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
cs.LG
Submitted: 2026-07-02
Updated: 2026-11-08
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Understanding the Role of Training Data in Test-Time Scaling
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- Effective Reasoning Chains Reduce Intrinsic Dimensionality
- Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
- LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
- Steering Language Models With Activation Engineering
- From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
- Qwen2 Technical Report
- The Geometry of Reasoning: Flowing Logics in Representation Space
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning