Add new multi-agent papers to README

We got 4 new papers: Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy (NIPS2024) Simulating Human-like Daily Activities with Desire-driven Autonomy (ICLR2025) CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games (ACL 2025 SAC highlight) Probe by Gaming: A Game-based Benchmark for Assessing Conceptual Knowledge in LLMs (Arxiv) thanks!