Salesforce Releases BehaviorBench for Predicting User Decisions
Building agents that model actual human behaviour has relied on synthetic personas, and this benchmark offers a measurable, open alternative with licensed data. Teams developing personalised assistants or recommendation agents can use it to evaluate how well their models exploit user history. The Apache-2.0 release on Hugging Face makes it directly usable without licensing friction.
Salesforce Research introduced BehaviorBench, a benchmark that tests whether AI models can predict a person's next decision from real public decision records instead of simulated users. The dataset covers 2,000 users and includes 141K Belief instances and 1.48M Trade instances. Personal history raises model accuracy from roughly 53% to up to 75%. The results also show that profiles help predict overall stance while recent history better predicts next actions. The benchmark is openly available on Hugging Face under the Apache-2.0 license.
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces: https://t.co/tKvAlxGFIc
Useful agents need to understand the people they serve. BehaviorBench tests whether models can predict a person's next decision from real public decision records in place of simulated users.
→ 2,000 users, 141K Belief + 1.48M Trade instances → Personal history lifts accuracy from ~53% to up to 75% → Profiles help predict overall stance; recent history helps predict next actions → Openly available on Hugging Face (Apache-2.0)
#FutureOfAI #AgenticAI #EnterpriseAI
