AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control logic, and rule-based fallbacks are hidden, while each decision can have monetary consequences. We ask whether an agent can predict an unfamiliar counterpart's next decision from a few interactions. To avoid real-world logging confounds, we study this problem in controlled bargaining and negotiation games, formulating it as target-adaptive text-tabular prediction: each decision point is a table row combining structured game state, offer history, and dialogue, while $K$ previous games of the same target agent, i.e., the counterpart being modeled, are provided in the prompt as labeled adaptation examples. Our model is built on a tabular foundation model that represents rows using game-state features and LLM-based text representations, and adds LLM-as-Observer as an additional representation: a small frozen LLM reads the decision-time state and dialogue; its answer is discarded, and its hidden state becomes a decision-oriented feature, making the LLM an encoder rather than a direct few-shot predictor. Training on 13 frontier-LLM agents and testing on 91 held-out scaffolded agents, the full model outperforms direct LLM-as-Predictor prompting and game+text features baselines. Within this tabular model, Observer features contribute beyond the other feature schemes: at $K=16$, they improve response-prediction AUC by about 4 points across both tasks and reduce bargaining offer-prediction error by 14%. These results show that formulating counterpart prediction as a target-adaptive text-tabular task enables effective adaptation, and that hidden LLM representations expose decision-relevant signals that direct prompting does not surface.

翻译：AI代理在自然语言中与陌生对手进行谈判和交易：例如，面对未知卖方的买方机器人，或与供应商谈判的采购助手。在此类交互中，对手的大型语言模型（LLM）、提示词、控制逻辑以及基于规则的备用机制均为隐藏状态，而每次决策都可能产生货币后果。我们探究代理能否通过少量交互预测陌生对手的下一步决策。为避免现实场景中的日志混杂效应，我们在受控的讨价还价与谈判游戏中研究该问题，并将其形式化为目标自适应文本表格预测任务：每个决策点对应表格中的一行，结合了结构化游戏状态、报价历史及对话，同时将同一目标代理（即被建模的对手）的K场先前游戏作为标记自适应示例提供至提示中。我们的模型基于表格基础模型构建，该模型利用游戏状态特征和基于LLM的文本表示对行进行编码，并引入"LLM作为观察者"作为附加表示：一个冻结的小型LLM读取决策时刻的状态与对话；其回答被丢弃，而隐藏状态成为面向决策的特征，使LLM成为编码器而非直接的小样本预测器。基于13个前沿LLM代理的训练，并在91个保留的脚手架代理上进行测试，完整模型优于直接使用"LLM作为预测器"的提示策略及游戏+文本特征基线。在该表格模型中，观察者特征的贡献超越其他特征方案：在K=16时，两项任务中的响应预测AUC均提升约4个百分点，且讨价还价报价预测误差降低14%。结果表明，将对手预测构建为目标自适应文本表格任务可实现有效适应，且隐藏的LLM表示能揭示直接提示无法呈现的决策相关信号。