Dyad represents two parts of an agent separately: the LLM encodes the evolving interaction and performs language-based reasoning, while an environment-conditioned encoder embeds every candidate action independently and in parallel.
Typed action encoding helps language models learn adaptable agent policies
Dyad separates language reasoning from structured action selection, enabling efficient decisions over changing action spaces.
Big Tech
Yundaichuan Zhan · Weishi Wang · Wenbiao Liu · Daniel Dahlmeier · Chengwei Qin · Juncheng Li · +2 more
Zhejiang University · SAP · Central South University · The Hong Kong University of Science and Technology (Guangzhou) · Chalmers University of Technology
Research Digest··2 min read
Zhan et al.
Why this paper
From Microsoft Research and 5 others
In one line
An architecture called Dyad adds a typed action encoder to LLMs, improving agent decision-making and general capabilities.
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
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§