# User Simulation

A user simulator now writes a first-person evaluation of the assistant before producing its next line, including a 1-to-5 rating and a critique-or-praise judgment; on real user-ChatGPT logs it tracks human users better than prompted simulators of the same size, and it lets multi-turn RL train assistants to comparable quality with less than half the compute.

A user simulator now writes a first-person evaluation of the assistant before producing its next line, including a 1-to-5 rating and a critique-or-praise judgment; on real user-ChatGPT logs it tracks human users better than prompted simulators of the same size, and it lets multi-turn RL train assistants to comparable quality with less than half the compute.

For repository-level software development, researchers built ReqClarifyBench, pairing 341 tasks with vague user intents, human-validated requirement documents, and code evaluation artifacts, and ran multi-turn clarification with simulated users carrying three real-world personas. Across six LLMs, asking effectively did not mean writing better documents: the strongest questioner scored lower on requirement alignment, yet adding interactive clarification raised average alignment from 0.212 to 0.494, a 133.1% relative gain, with code-generation scores rising too.

For repository-level software development, researchers built ReqClarifyBench, pairing 341 tasks with vague user intents, human-validated requirement documents, and code evaluation artifacts, and ran multi-turn clarification with simulated users carrying three real-world personas. Across six LLMs, asking effectively did not mean writing better documents: the strongest questioner scored lower on requirement alignment, yet adding interactive clarification raised average alignment from 0.212 to 0.494, a 133.1% relative gain, with code-generation scores rising too.

A language model learns behavioral reasoning from prediction-market price movements, reaching 0.674 directional accuracy on Polymarket and transferring zero-shot to four user-simulation benchmarks without any individual-level annotations.

A language model learns behavioral reasoning from prediction-market price movements, reaching 0.674 directional accuracy on Polymarket and transferring zero-shot to four user-simulation benchmarks without any individual-level annotations.