---
title: "Structured Machine Theory of Mind from Agent Trajectories"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07208v1"
permalink: "https://feed.astralor.com/items/itm_9b32c359bcf5fb42b17aa7e2"
published: "2026-11-04T22:56:30.000Z"
score: 61
channel: "tech"
tags: ["AI Agent","多模态","Structured Machine Theory","Mind","Agent Trajectories Predictive","Such","Predictive"]
---

# Structured Machine Theory of Mind from Agent Trajectories

## 速览

Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior. Such models support prediction but not…

## 关键点

- Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior.
- Such models support prediction but not principled intervention: they cannot answer how an agent's behavior would change if its beliefs or preferences were different.
- We introduce Structured Machine Theory of Mind (SMToM), a framework that attributes explicit, independently supervised belief and desire representations from observed trajectories within a Belief-Desire-Intention (BDI) …

## 全文

Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior. Such models support prediction but not principled intervention: they cannot answer how an agent's behavior would change if its beliefs or preferences were different. We introduce Structured Machine Theory of Mind (SMToM), a framework that attributes explicit, independently supervised belief and desire representations from observed trajectories within a Belief-Desire-Intention (BDI) causal structure. The central architectural element is a goal head that consumes only the predicted mental-state channels and a current-trajectory embedding; counterfactual intervention on beliefs and desires is a direct operation. We instantiate SMToM on a controlled pedestrian navigation domain where ground-truth mental states are known by construction, enabling evaluation of attribution accuracy, local channel interventions, and trajectory-level counterfactual diagnostics. The resulting model, BDIBottleneck, improves over trajectory-only and unsupervised-context neural baselines. It is also competitive with a matched auxiliary-supervised context baseline while providing an editable mental-state interface that the unbottlenecked baseline lacks. Counterfactual experiments on desires confirm that substituting an agent's inferred preferences with a different activity type coherently shifts predicted destinations toward relevant locations. Counterfactual experiments on beliefs confirm that marking a location as unavailable in the agent's belief state reduces its predicted probability as a destination, though in a complex way. These results demonstrate, in a controlled navigation setting, that explicit BDI-structured supervision is a viable foundation for interpretable and counterfactual analysis of longitudinal trajectory data.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_9b32c359bcf5fb42b17aa7e2