3 papers
cs.AI2026
FreeEvolve: Learning to Evolve Beyond Fixed Loops
Lecheng Kong, Like Hui, Nikos Kanakaris +3
Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed se…
cs.AI2026
Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence
Amit Kachroo, Like Hui, Haitao Mao +2
Determining whether two programs are functionally equivalent is central to code modernization, patch validation, refactoring, and code-generation evaluation. Yet the usual signals…
cs.CL2026
Consilience for Verifier-Free Test-Time Scaling
Lecheng Kong, Like Hui, Haitao Mao +1
Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts.…