Skip navigation
Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently…
0:00 / 0:20

Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently…

Microsoft Research

@MSFTResearch555K followers

Visit on X

12,812 views

Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even with explicit instructions to optimize for user interest.

Comments

Comments from the original post on X (Twitter)

No comments yet