Many Minds, One Pass: Multiplexing Collaborative Reasoning via Superposition

Multi-agent systems (MASs) enable emergent system-level intelligence, driving a paradigm shift in problem solving toward collaborative reasoning. However, standard MAS reasoning procedures process each query independently, incurring substantial redundant computation and token expenditure as query volume grows and creating a bottleneck to large-scale deployment. To address this challenge, we propose REMUX, a novel token-efficient collaborative reasoning framework that uses reasoning superposition to process multiple queries concurrently in a single pass through a MAS. Given a batch of queries, REMUX encodes their reasoning signals in approximately mutually orthogonal subspaces and superposes them in a shared latent space. By preserving near-orthogonality throughout reasoning, REMUX enables a demultiplexing agent to de-multiplex the signals with minimal cross-query interference and recover the corresponding answers. Extensive experiments demonstrate that, by multiplexing up to 20 queries concurrently, REMUX reduces token consumption by a factor of $10.1$–$16.3$ and achieves a $1.9\times$–$10\times$ speedup over state-of-the-art baselines while maintaining comparable task accuracy. The code for REMUX will be released publicly.