3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work identifies a systematic failure mode in RL-trained retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon the authors term confident hallucination, and addresses this with a faithfulness-gated reward design.
These results show that verified synthetic environments can serve as a scalable and reliable training substrate for compact web agents, shifting synthetic webagent learning from surface-level plausibility toward executable, state-grounded supervision.
Results show that organizing solver feedback into generation, verification, and repair roles enables more scalable and faithful annotation-free symbolic planning.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
