FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

arXiv:2609.27657 · cs.LG, cs.AI, cs.CL · Submitted 2026-09-23 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/Alexiush/fleet

Terminology

• Accuracy — 17× in this paper · explained in 1 episode
• Benchmark — 11× in this paper · explained in 2 episodes
• Calibration — 11× in this paper · explained in 7 episodes
• Verifier — 7× in this paper · explained in 2 episodes
• Clustering — 6× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Disjoint Set Union — 5× in this paper
• Outcome Reward Model — 5× in this paper
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Test-time Scaling — 5× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Monte Carlo Tree Search — 3× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Gaussian Mixture Model — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptive Decoding — 1× in this paper · explained in 1 episode
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Standardized Benchmarks — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Vector Representations — 1× in this paper · explained in 2 episodes

Sources

• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Evaluating Large Language Models Trained on Code
• Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
• A Law of Next-Token Prediction in Large Language Models
• The Curious Case of Neural Text Degeneration
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• LLMs Get Lost In Multi-Turn Conversation
• Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
• Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
• Training language models to follow instructions with human feedback
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions
• A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
• A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
• Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks