Search papers, labs, and topics across Lattice.
4
0
4
20
Change2Task recovers 29.2% more verified coding tasks than traditional methods, streamlining the training of coding agents.
Lax bug reproduction tests can lead to plausible but incorrect patches, but a new iterative framework boosts repair success by refining both tests and fixes.
Coding agents can generate observability artifacts, but they miss key diagnostic semantics, exposing fault signals for only 13.99% of failures.
Knowing the *perfect* API to use or *exact* location to edit could drastically improve SWE agent performance, but knowing the perfect regression test result? Not so much.
