Co-Evolving Acting and Forecasting for Language Agents
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits this supervision through value targets that estimate per-step success probabilities or observation targets that fit environment response.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
