Public articles linked to the same research event.
arXiv The work introduces Code2Math, a multi-agent framework in which code agents autonomously evolve existing math problems into more complex variants while validating the solvability and increased difficulty of the generated problems; experiments show that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals, providing empirical evidence that code-driven agents can serve as a mechanism for synthesizing high-difficulty mathematical reasoning problems in scalable computational environments.
The work introduces Code2Math, a multi-agent framework in which code agents autonomously evolve existing math problems into more complex variants while validating the solvability and increased difficulty of the generated problems; experiments show that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals, providing empirical evidence that code-driven agents can serve as a mechanism for synthesizing high-difficulty mathematical reasoning problems in scalable computational environments.
The work introduces Code2Math, a multi-agent framework in which code agents autonomously evolve existing math problems into more complex variants while validating the solvability and increased difficulty of the generated problems; experiments show that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals, providing empirical evidence that code-driven agents can serve as a mechanism for synthesizing high-difficulty mathematical reasoning problems in scalable computational environments.
The work introduces Code2Math, a multi-agent framework in which code agents autonomously evolve existing math problems into more complex variants while validating the solvability and increased difficulty of the generated problems; experiments show that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals, providing empirical evidence that code-driven agents can serve as a mechanism for synthesizing high-difficulty mathematical reasoning problems in scalable computational environments.