Nicolas Flammarion, Francesco Angelo, Hristo Papazov
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We explore the possibility of exact algorithmic learning with gradient-based methods and introduce a differentiable framework capable of strong length generalization on arithmetic tasks. Our approach centers on Differentiable Finite-State Transducers (DFSTs), a Turing-complete model family that avoids the pitfalls of prior architectures by enabling constant-precision, constant-time generation, and end-to-end log-parallel differentiable training. Leveraging policy-trajectory observations from expert agents, we train DFSTs to perform binary and decimal addition and multiplication. Remarkably, models trained on tiny datasets generalize without error to inputs thousands of times longer than the training examples. These results show that training differentiable agents on structured intermediate supervision could pave the way towards exact gradient-based learning of algorithmic skills. Code available at https://github.com/dngfra/differentiable-exact-algorithmic-learner.git.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2511.22751")
get_code_for_paper("2511.22751")
have("2511.22751")
Connect an agent — have() is free.