Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
State-of-the-art coding agents exhibit critical boundary violations, with nearly all misinterpreting dependencies and over half compromising environment integrity or user inputs.
High Pass@1 masks a critical failure mode in frontier code models: models routinely ship bloated, unreviewable diffs for trivial bugs, an issue that scaling cannot solve but RL post-training can directly optimize.
Optimal mixing of query translations can significantly boost retrieval performance, but English dominance complicates the landscape of multilingual querying.
