# Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling Page: https://stenobird.com/podcast/daily-paper-cast-7079649/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling.md Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649) Published: 2026-05-15T05:00:32+00:00 Episode link: https://share.transistor.fm/s/3a7cb92e Audio file: https://media.transistor.fm/3a7cb92e/0f41ef99.mp3 Processing state: not_requested JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling Duration seconds: 1499 ## Resource šŸ¤— Upvotes: 43 | cs.LG, cs.AI, cs.CL, cs.MA Authors: Eilam Shapira, Moshe Tennenholtz, Roi Reichart Title: Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling Arxiv: http://arxiv.org/abs/2605.12411v1 Abstract: 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-pā€¦ ## Actions - request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling/transcription-requests` ā€” Idempotently request low-priority transcript generation for this episode. - read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling.md` ā€” Read the agent-friendly Markdown representation of this episode resource. A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed. ## Transcript Full transcripts are not published on public pages unless there is a clear rights basis.