Mateusz Bystroński

We argue that LLM-based coding agents frequently fail to solve problems that lie within the model’s capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and int...

Before a tax authority can issue a ruling, it must receive a complete description of the taxpayer’s situation—yet no benchmark measures whether language models can systematically elicit all relevant facts through dialogue.We introduce FSDBench ( Factual State Discovery Benchmark ), in which a dis...

Starting from the observation that conditioning a poetry-writing prompt with a pancake recipe leads an LLM to produce a coherent poem incorporating pancake-related content and, more broadly, that such contexts arrange themselves into a structured semantic vector space, we argue that this renders...