Institution profile

Zhongguancun Institute of Artificial Intelligence

Academic institutionasia · cn
Official website
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets

Aug 08, 2026

This work addresses the high cost of ground-truth evaluation—such as high-fidelity simulation or physical experimentation—that limits large language model (LLM)-driven program discovery in scientific and engineering domains. To overcome this bottleneck, the authors propose Janus, a novel framework that co-evolves target programs and executable agent evaluators. Janus leverages LLMs to generate task-specific evaluators and integrates region-conditioned composition, online credit assignment, and a closed-loop validation mechanism with real-world feedback. This approach efficiently guides the search process under label scarcity and distributional shift. Evaluated across five diverse tasks, Janus achieves 99% of baseline performance using only 40.9% of the ground-truth evaluations on average, substantially improving sample efficiency and the accuracy of candidate ranking.

0 citationsRead paper
Recent publications

Latest Papers

Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets

Aug 08, 2026

This work addresses the high cost of ground-truth evaluation—such as high-fidelity simulation or physical experimentation—that limits large language model (LLM)-driven program discovery in scientific and engineering domains. To overcome this bottleneck, the authors propose Janus, a novel framework that co-evolves target programs and executable agent evaluators. Janus leverages LLMs to generate task-specific evaluators and integrates region-conditioned composition, online credit assignment, and a closed-loop validation mechanism with real-world feedback. This approach efficiently guides the search process under label scarcity and distributional shift. Evaluated across five diverse tasks, Janus achieves 99% of baseline performance using only 40.9% of the ground-truth evaluations on average, substantially improving sample efficiency and the accuracy of candidate ranking.

0 citationsRead paper