Hidden Messages Between Diffusion LM Agents: Causal Evidence for Latent Communication
ITMO · hf · 2026-10-23
A paper from ITMO and HSE University provides causal evidence that diffusion language model agents can exchange compressed continuous hidden messages. Since diffusion LMs form answers through revisable continuous states that multi-agent systems usually discard, the authors test whether one diffusion trajectory can pass a compact hidden message into another — and show the receiver causally uses its meaning, with transfer timing sometimes outweighing repeated exchanges.
More from Research
- MathEconLib open-sourced: Axiom Math and top economists bring machine-checked proofs to economics in Lean 4 — soumitrashukla9 · 2026-10-23
- Ken Ono invites the community to build MathEcon on the new Lean 4 economics library — soumitrashukla9 · 2026-10-23
- IFM open-sources RL360: 8,192 concurrent sandboxes and ~1.3M rollouts for agentic RL — rupspace · 2026-10-23
- Science lifts expression of concern on 2024 AI debunking-conspiracies paper; conclusions unchanged — DG_Rand · 2026-10-23
- Embodied First Exam benchmarks coding agents on 1,090 tasks across 44 robots — ManlingLi_ · 2026-10-23
- Anima Anandkumar on neural operators: AI weather models beat supercomputers — AnimaAnandkumar · 2026-10-23