Towards Better Exploration in Sequential Test-Time Scaling

arXiv:2609.39632 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-10-02

Terminology

• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
• Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
• On the Measure of Intelligence
• From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
• Gemma 3 Technical Report
• Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
• Qwen3 Technical Report
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Geometric Dynamics of Agentic Loops in Large Language Models
• Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
• Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
• Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
• Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing
• Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
• Do Language Models Converge to Themselves? Recursive Self-Refinement as Textual Relaxation
• Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks