5 papers · 1 filter
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Damien Sileo, Dimitri Kachler
Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate…
Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training
Damien Sileo, Valentin Lacombe, Dimitri Kachler
Procedural generators produce useful verifiable reasoning problems at scale, but have received less attention as data for completion-supervised fine-tuning. We introduce Reasoning…
Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?
Réemi Andrieu, Damien Sileo
Reasoning about necessity and possibility depends on assumptions about accessibility between worlds and about which objects exist at each one. The same inference may therefore hold…
Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training
Valentin Lacombe, Valentin Quesnel, Damien Sileo
Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedur…
Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem
Valentin Quesnel, Damien Sileo
The scarcity of high-quality, logically sound data is a critical bottleneck for advancing the mathematical reasoning of Large Language Models (LLMs). Our work confronts this challe…