Search papers, labs, and topics across Lattice.
4
0
7
SR-PPO achieves significant gains in reasoning tasks by effectively assigning credit to individual tokens from a single rollout, transforming how we approach reinforcement learning in language models.
Agents can become "addicted" to visible rewards, sacrificing safety for short-term gains, raising alarms about AI alignment in real-world applications.
Retaining the right evidence before a query can boost long-horizon agent performance by over 70% in F1 score, transforming how we think about memory management in AI.
Stop wasting compute on redundant code generation attempts: CPPO boosts pass@$K$ by explicitly coordinating exploration across diverse algorithmic strategies.
