arXiv:2608. 11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks.
arXiv:2608. 03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation.
QEncodeBench evaluates whether large language models can translate classical constraint problems into verified quantum phase oracles. The benchmark measures the correctness of generated circuits using an adversarial self‑validated verifier that checks full solution‑set equivalence while enforcing resource limits. Results show that models lacking a reasoning mode perform poorly, whereas enabling native reasoning improves accuracy tenfold; semantic errors dominate, and neuro‑symbolic pipelines close most gaps by delegating critical composition to deterministic procedures.
Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes.
QART is a quantum‑classical hybrid architecture that augments a language model with quantum encoding, CIM‑based QUBO optimization, and quantum decoding to improve long‑horizon reasoning. The authors claim that, under certain assumptions, QART can maintain a non‑zero probability of recovering an optimal reasoning path while traditional autoregressive LLMs see their acceptance probability drop to zero as cumulative risk grows. Experiments on six benchmarks with three backbone models show that QART outperforms the baselines in 14 of 15 pairings, with relative gains up to 84.0% on SciCode.
arXiv:2609.05842v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards enables large language models to think slowly, but the same training can induce policy collapse: proba...
arXiv:2606. 11673v1 Announce Type: cross Abstract: Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order-$k$ interaction is known to require either super-quadratic resources in one layer or composition across depth.
arXiv:2604. 14501v2 Announce Type: replace-cross Abstract: We study how depth, finite precision, state dimension, and chain-of-thought (CoT) affect the expressive power of multi-layer state-space models (SSMs).
arXiv:2606. 19697v1 Announce Type: cross Abstract: The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation.
arXiv:2607. 02444v1 Announce Type: cross Abstract: We study stabilizer state testing and learning with limited coherent quantum memory.
We study stabilizer state testing and learning with limited coherent quantum memory. Here an algorithm sequentially receives copies of an unknown $n$-qubit state, but may keep only $k$ qubits of coherent quantum memory between measurements.
arXiv:2607. 24714v1 Announce Type: cross Abstract: Trapped-ion quantum computers rely on shuttling compilers, which cast an input algorithm into a sequence of ion-qubit movements within a given architecture.
The paper investigates whether having only forward access to a state-preparation unitary—without its inverse—can reduce the number of queries needed for quantum PAC learning. By analyzing worst-case scenarios over all compatible unitaries and finite dimensions, the authors prove that the optimal forward-only query complexities for realizable and agnostic learning are θ((d+log(1/δ))/ε) and θ((d+log(1/δ))/ε²), respectively, matching classical and quantum-copy bounds. These results demonstrate that forward-only access offers no asymptotic advantage over classical data or quantum copies, highlighting the essential role of inverse access for any improvement in the realizable setting.