2 papers
cs.AI2026
Measuring Reward-Seeking via Contrastive Belief Updates
Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya +5
Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure be…
cs.SE2025
A benchmark for vericoding: formally verified program synthesis
Sergiu Bursuc, Theodore Ehrenborg, Shaowei Lin +10
We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications - in contrast to vibe coding, which generates potentia…