Microsoft Research: Small Language Models Learn Strategic Negotiation via SocialRL
pswider · x · 2026-08-05
Microsoft Research announced several new advancements:
- SocialRL: A framework helping Small Language Models (SLMs) develop strategic social reasoning skills for negotiation, preventing them from being overly agreeable when representing user interests.
- EvoLib: Enables AI agents to transform past experiences into evolving knowledge, improving performance over time.
- Reliable A/B Testing: New methods improve testing reliability by addressing correlated metrics and reducing false discoveries.
- PazaBench V2: Expands speech recognition evaluation across diverse African languages and countries.
- Project Ex Vivo: Explores advancing precision oncology by using AI to model cancer as a dynamic system.
More from coding & agent
- Anthropic Releases Free 1-Hour Workshop on Loop Engineering — goyalshaliniuk · 2026-08-05
- OpenAI's Codex Shows Monopolistic Trend, Squeezing Native Agent Frameworks — vista8 · 2026-08-05
- Microsoft's AgentStream: Evaluating Self-Evolving LLM Agents in Streaming Tasks — microsoft · 2026-08-05
- AI Agent Learns New Skills Autonomously: 8-Agent Loop Scours GitHub for Workflows — alexcovo_eth · 2026-08-05
- Pitfall: Claude API Skill Descriptions May Trigger Safety Classifiers — voooooogel · 2026-08-05
- Dev Workflow: 90% Codex, Drops Kimi K3 for GPT-5.6 Luna Max — DeryaTR_ · 2026-08-05