PhantomEnvironments: Training LLM Agents in Fictional Worlds
Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. W...
Anmol Kabra, Swathi Saravana Selvam, Albert Gong et al.
· 0 citations