---
title: "Belief-Contraction-Driven Active Inverse Source Localization and Characterization"
authors:
  - "Yiwei Shi"
  - "Mengyue Yang"
  - "Qi Zhang"
  - "Cunjia Liu"
  - "Weinan Zhang"
  - "Weiru Liu"
doi: "10.24963/ijcai.2026/726"
url: "https://ijcai.org/proceedings/2026/726"
pdf: "https://ijcai.org/proceedings/2026/0726.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6528-6535"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Advanced AI4Tech: Deep AI4Tech"
  - "Advanced AI4Tech: AI4Tech foundations"
  - "Advanced AI4Tech: Data-driven AI4Tech"
---

# Belief-Contraction-Driven Active Inverse Source Localization and Characterization

Yiwei Shi, Mengyue Yang, Qi Zhang, Cunjia Liu, Weinan Zhang, Weiru Liu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6528-6535. DOI: [10.24963/ijcai.2026/726](https://doi.org/10.24963/ijcai.2026/726)

## Abstract

Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer latent source parameters from sparse, noisy readings. We introduce a belief-contraction-driven approach that unifies inference, stopping, and control. An attention-augmented particle filter stabilizes Bayesian belief updates through ESS-based resampling, feature-aware sparse attention smoothing, and Metropolis–Hastings rejuvenation that preserves the filtering posterior. Belief contraction (posterior dispersion) defines both a termination rule and a goal-aligned intrinsic reward, enabling reinforcement learning without distance-to-source shaping. Across seven field modalities, spatial out-of-distribution tests, and nonstationary source shifts, our agent (ATT-PFRL) achieves higher completion, faster convergence, and more accurate localization than planning and RL+Bayes baselines under similar computation. Fixed-trajectory studies also show improved ESS and lower RMSE, isolating the benefit of the inference layer.