- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies byte-budgeted latent communication between LLM agents that each hold part of the evidence for a multiple-choice decision. InnoComm compresses each sender's hidden states into a few 128-dimensional INT8 slots that a frozen 7B receiver reads through a memory adapter, and it can also co-train that adapter with the codec. On two decision tasks built from FEVEROUS and MuSiQue, co-adaptation lowers NLL by 0.043 relative to a matched codec-only continuation at 146 bytes per sender.
Critical strengths
- Rigorous accounting of communication cost. All interfaces are measured with realized application-layer bytes through an executable serialization path.
Critical weaknesses
-
The central premise is not supported, because text dominates the risk–byte frontier. At 397 bytes/request the best latent packet loses to byte-matched text and to hard-capped head-truncated text with fewer bytes (both with an adapted text receiver). And native full text beats every latent endpoint. Given this, the paper does not show any regime in which one would choose InnoComm over sending (truncated) text.
-
Results on real multi-agent settings are absent, so generality is unclear.
Questions for authors
-
In what realistic deployment regime do latent packets beat byte-matched text? Can you show an experiment where InnoComm is on the Pareto frontier?
-
How does InnoComm compare with existing latent-communication methods and context-compression methods under the same byte accounting?
-
Does the approach transfer to open-ended multi-agent tasks, and can the codec generalize across tasks without re-training?