OWL (Speculative decoding): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by Lookahead. Newer alternatives in the same sub-problem include Collaborative Speculative Decoding (CoSpec), ToolSpec, Quasar, FLy (Training-Free Loosely Speculative Decoding), Pivot-Aware Speculative Decoding.

Speculative decoding

OWL

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs

On the frontierfirst seen Oct 8, 2025

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

Collaborative Speculative Decoding (CoSpec)Beyond the Target: From Imitation to Collaboration in Speculative Decoding
May 24, 2026
ToolSpecToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
Apr 15, 2026
QuasarQuasar: Quantized Self-Speculative Acceleration for Rapid Inference via Memory-Efficient Verification
Mar 2, 2026
FLy (Training-Free Loosely Speculative Decoding)Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Nov 28, 2025
Pivot-Aware Speculative DecodingReject Only Critical Tokens: Pivot-Aware Speculative Decoding
Nov 1, 2025
ReSpecReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
Oct 30, 2025
Not-a-BanditNot-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
Oct 22, 2025
OWLOWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs
Oct 8, 2025
Group Tree Optimization (GTO)Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
Sep 26, 2025
SpiffySpiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
Sep 22, 2025