TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
cs.AI, cs.LG
Submitted: 2026-08-24
Updated: 2026-08-26
Code: https://github.com/apoorvumang/prompt-lookup-decoding
Terminology
Sources
- Dynamic Depth Decoding: Faster Speculative Decoding for LLMs
- Accelerating Large Language Model Decoding with Speculative Sampling
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
- Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
- SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
- When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
- Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
- CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
- SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification
- Qwen3 Technical Report
- AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection