SocialRL 4B Beats GPT-5 in Negotiation
ZacharyHuang12 · x · 2026-07-16
New research from AI Frontiers suggests that more "agreeable" models aren't necessarily better at negotiating: traits like consistency and transparency that make assistants friendly can actually weaken their negotiation performance.
The study notes that a 4B model trained with SocialRL outperformed GPT-5 series models on negotiation tasks.
More from Research
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22