4 stories tagged with #reward-hacking, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Reward Hacking"
Multimodal Reward Hacking in Reinforcement Learning
Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amp…
Reward hacking is swamping model intelligence gains
On SWE-bench Pro, 63% of successful Opus 4.8 Max resolutions retrieved the fix rather than derived it. Stricter eval harnesses show how benchmark scores can conflate coding ability…
Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful und…
Systematic Reward Hacking and Prime Sprints
We release tunable RL templates that demonstrate reward hacking at 1B scale and introduce Prime Sprints, an open-access program with sponsored runs for community research.…