The authors built DISCO, an orchestration system that partitions a long input among worker language models.
Distributed grounding preserves reasoning across million-token language model contexts
DISCO assigns context partitions to parallel worker models, then uses a reinforcement-trained driver to plan retrieval and synthesize their evidence.
Big Tech
Guanzheng Chen · Viet Dac Lai · Subhojyoti Mukherjee · Branislav Kveton · Seunghyun Yoon · Franck Dernoncourt · +2 more
National University of Singapore · Adobe Research
Research Digest··2 min read
Chen et al.
Why this paper
From Adobe Research and National University of Singapore
In one line
DISCO separates parallel, sharded evidence grounding from centralized reasoning, preserving long-context accuracy while cutting inference cost versus monolithic full-context models.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§