IB-RL让对话双方独立对练，不靠固定对手。车销任务89.6% vs 基线84.6%，还胜过DeepSeek V4 Pro。
现有强化学习RL训练对话智能体时通常针对固定对手，导致策略利用对手特定规律，作者将其称为静态对手不匹配问题。为此提出的IB-RL让对话双方通过联合轨迹共同进化，但各自用独立优势、动作掩码和更新路径优化自身奖励。在Vehicle TeleSales任务上，IB-RL取得89.6%的Success@1，超过最优单边基线84.6%。在Deal-or-NoDeal任务中，IB-RL对DeepSeek V4 Pro达到98.4%的一致率，而最优单边基线仅86.4%。
IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents
Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution. In these settings, the environment follows fixed rules and does not adapt strategically to the agent. Strategic dialogue differs in this respect: the environment is another agent that adapts to the policy, and success depends on the interaction between the two sides. Despite this interactive nature, current RL approaches typically train a target agent against a fixed counterpart or simulator. We find that this training paradigm encourages the policy to exploit counterpart-specific regularities rather than learn strategies that generalize across counterparts. We call this problem the static-counterpart mismatch, which we quantify directly in our experiments. To address it, we propose Isolated Bilateral Reinforcement Learning (IB-RL), in which the two roles coevolve through joint rollouts while each role optimizes its own reward through fully independent advantages, action masks, and update paths. We evaluate frozen policies against fully independent held-out counterparts in both domains. On Vehicle TeleSales, IB-RL achieves 89.6% Success@1, compared to 84.6% for the best unilateral RL baseline. On Deal-or-NoDeal, it reaches 98.4% agreement against DeepSeek V4 Pro, compared to 86.4% for the best unilateral baseline. These results indicate that jointly training both roles with strict peragent isolation produces policies that generalize more effectively to unseen counterparts.