Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Youwei Liu, Jian Wang, Hanlin Wang +1
Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, existing textual world models…
cs.AI2026
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
Keyu Li, Junhao Shi, Yang Xiao +11
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain f…