Microsoft Research: 4B model tuned with SocialRL out-negotiates GPT-5 family

dair_ai · x · 2026-08-17

New work from Microsoft Research shows a 4B parameter model can be tuned to out-negotiate the GPT-5 family of models.

Key findings:

The dispositions that make an assistant pleasant make it a poor delegate: a friendly frontier model volunteers its principal's private information and concedes at the first sign of resistance.
SocialRL trains social reasoning directly in a 4B model across six principal-driven domains including negotiation, job interviews and marketplace haggling.
After training, 78% of buyer openings anchor below target, versus 3% untrained.
Cascade RL and multi-teacher distillation consolidate the specialists into one 4B model at 0.627 average utility, beating GPT-5.1 (0.619) and GPT-5.2 (0.613).

More from Models