Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance

arXiv:2609.24066 · cs.CL · Submitted 2026-09-21 · Read on arXiv

cs.CL

Submitted: 2026-09-21

Updated: 2026-09-21

Code: https://github.com/rattlesnakey/SPS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 85× in this paper · explained in 2 episodes
• Benchmark — 34× in this paper · explained in 2 episodes
• Direction Bank — 29× in this paper
• Calibration — 28× in this paper · explained in 7 episodes
• Clustering — 11× in this paper · explained in 2 episodes
• AUC — 9× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• State Matching — 8× in this paper
• Uncertainty Gate — 7× in this paper
• Entropy-Adaptive Strength — 5× in this paper
• Verifier — 5× in this paper · explained in 2 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Activation Steering — 3× in this paper · explained in 4 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Linear Probing — 3× in this paper · explained in 2 episodes
• Representation Engineering — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive Steering — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Best-of-N Sampling — 1× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Entropy-Triggered Temperature — 1× in this paper
• F1 Score — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• State-conditioned Progressguided Steering — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• From System 1 to System 2: A Survey of Reasoning Large Language Models
• SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
• OpenAI GPT-5 System Card
• Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
• Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
• MMFormalizer: Multimodal Autoformalization in the Wild
• Qwen3 Technical Report
• Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
• Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
• Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
• Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
• Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
• First Return, Entropy-Eliciting Explore

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering