The authors built Hermes, a hierarchy of configurable inference harnesses.
Models Learn to Allocate Context and Scale Inference More Effectively
Hermes-Learn trains language models to decide when to open, delegate to, and reuse separate reasoning contexts.
Big Tech
Xinyu Li · Mononito Goswami · Hao Liu · Nikos Kanakaris · Langlin Huang · Prithwish Jana · +2 more
Carnegie Mellon University · AWS AI Labs · Washington University in St. Louis · Georgia Institute of Technology
Research Digest··3 min read
Li and colleagues study contextual reasoning, the ability to allocate multiple context windows and decide what information should pass between them during inference.
Why this paper
From AWS AI Labs and 3 others · Part of Context Engineering for Agents, now 41 papers
In one line
A model's ability to choose how to allocate and reuse contexts during inference can be learned, enabling test-time scaling.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§