Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for coding problems mainly comes from specific test cases, where high-quality test cases are often scarce since they should be both sound and discriminative. We thus turn to study the auto-generation of test cases using the learned model. We find this is naturally an adversarial RL problem: the model is expected to generate effective test cases as counterexamples, depending on the solver’s current failure modes. We propose Test Cases Scaling (TCS), a two-stage RL framework for effective test generation. Both stages train a test generator from a rolling policy-aligned buffer: Stage 1 generates tests consistent with the reference solution, and Stage 2 restricts the buffer to current failure modes and learns counterexample tests. Across TACO and LiveCodeBench, TCS improves both pass@1 and inference-time answer selection according to generated tests. We find the learned test generator can also improve outputs from other LLMs to further improve their performance.

Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability, yet professional ESG analysis is hindered by data fragmentation and complex multi-step workflows. Existing ESG benchmarks rely on LLM-generated questions that often suffer from semantic ambiguity, limiting their diagnostic reliability. We introduce ESGAgent, a hierarchical multi-agent system with a domain-oriented toolset for automating end-to-end ESG workflows, and a three-level benchmark derived from 310 corporate sustainability reports, featuring expert-sourced questions with verified, unambiguous answers at Levels 1-2 and full report generation at Level 3. Evaluations across 20 state-of-the-art closed-source LLMs show that ESGAgent achieves 84.15% accuracy on Levels 1-2, surpassing the strongest baseline by 3.26 points, and produces Level 3 reports with higher factual consistency and analytical depth than commercial deep research systems, validated by both multi-LLM judging and human expert evaluation, showing a robust alignment (Pearson r=0.551).