cs.AINov 17, 2026

Long-Context Generation Is a Sampling Problem (When You Turn Up the Heat)

Authors: Allen G. Roush, Minh Nhat Nguyen, Ravid Shwartz-Ziv, Judah Goldfeder, Sanjay Basu

Organizations: Thoughtworks · Apart Research · New York University & Meta · Columbia University · 

Abstract

Open-weight language models are widely observed to get worse the longer they generate. Often, attempts to fix this involve more training. At high temperature, The sampler, i.e. the rule that picks the next token out of the model's probabilities, decides whether long and agentic generation survives and/or thrives. We test 29 open-weight models from 1B to 122B parameters on ten established benchmarks plus needle retrieval out to one million tokens, covering SWE-bench Verified coding agents, long chain-of-thought reasoning, long-form writing, long structured output and long-context reading. Samplers that keep their pool of candidate tokens small and steady as temperature rises don't lose accuracy. Samplers that let in low-probability tokens fall apart. At temperature 2, coding agents running top-p, top-k or Top-H resolve 0 of 100 GitHub issues, while the same agents running top-nsigma resolve 46 to 62 and win every issue the two samplers disagree on, on three Qwen3.5 models. Over all benchmarks top-nsigma keeps a median 100% of its temperature-1 score where top-p keeps 26%. Counting how many tokens each sampler lets through explains why. In one Llama-3.1-8B story, going from temperature 1 to 2 grows top-p's pool from 4 tokens to 51,845 while top-nsigma stays at 3. Across 133 combinations of sampler setting and temperature, the typical pool size predicts judged quality (Spearman correlation of -0.77), and when we pick the pool at temperature 1 and only apply temperature afterwards, Top-H, min-p and p-less stop collapsing. At the default temperature of 1 most samplers perform about the same, We release all code and data to the public.

Figures & tables

Appendix figures & tables34 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. One Temperature to Rule Them All?

    Nov 9, 2026Aviv Orly, Ori Shem-Ur, Yaron OzLLM InferenceDiversity-Aware Sampling

  2. Min-kk Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics

    Apr 13, 2026Yuanhao Ding, Meimingwei Li, Esteban Garces Arias +3Language Model DecodingAdaptive Inference