2 papers
cs.AI2026
Anchor: Preventing Artifact Drift for Reliable Agent Verification
Maksim Ivanov, Abhijay Rana
Reliable evaluation of long-horizon agents requires verifiers that match what the task actually asks. Verifiable rewards have driven progress in domains like math and coding, yet b…
cs.SE2026
Can Coding Agents Be General Agents?
Maksim Ivanov, Abhijay Rana, Gokul Prabhakaran
As coding agents have seen rapid capability and adoption gains, users are applying them to general tasks beyond software engineering. In this post, we investigate whether coding ag…