Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of
Frequent context compaction preserves task accuracy across long-horizon and long-input tasks, suggesting that long-context language models may be unnecessary and motivating semantic state space models.
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining short contexts. We further demonstrate that LLM performance does not collapse on long-horizon software engineering tasks even when taking at most one action per context, and based on that we outline the concept of semantic state space models (SSSMs). Our findings question the need for long-context language models.
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
You don't need long context was first seen on Hugging Face · Daily papers on Nov 4, 2026. Since then it has appeared in 10 checks on 2 different days. Its best position was #19 of 30, reached on Nov 5, 03:28 UTC. It dropped off the list after Nov 5, 15:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 5, 15:28 UTC, after 2 days of trending.
#19 on Hugging Face · Daily papers, on Nov 5, 03:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 4, 2026 and has been on the list on 2 days (10 checks) since.