# Belief Dynamics for Detecting Behavioral Shifts in Safe Collaborative Manipulation

arXiv: https://arxiv.org/abs/2604.04967 · HTML: https://mlsanity.com/paper/2604.04967/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Opponent Modeling in Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05559/) (2016)
- [Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1906.04737/) (2019)
- [Agent Modelling under Partial Observability for Deep Reinforcement Learning](https://mlsanity.com/paper/2006.09447/) (2020)

## Built on by (most cited first, 1 of 1)

- [VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation](https://mlsanity.com/paper/2604.25235/) (2026)

## Abstract (arXiv)

Robots operating in shared workspaces must maintain safe coordination with other agents whose behavior may change during task execution. When a collaborating agent switches strategy mid-episode, continuing under outdated assumptions can lead to unsafe actions and increased collision risk. Reliable detection of such behavioral regime changes is therefore critical. We study regime-switch detection under controlled non-stationarity in ManiSkill shared-workspace manipulation tasks. Across ten detection methods and five random seeds, enabling detection reduces post-switch collisions by 52%. However, average performance hides significant reliability differences: under a realistic tolerance of +-3 steps, detection ranges from 86% to 30%, while under +-5 steps all methods achieve 100%. We introduce UA-TOM, a lightweight belief-tracking module that augments frozen vision-language-action (VLA) control backbones using selective state-space dynamics, causal attention, and prediction-error signals. Across five seeds and 1200 episodes, UA-TOM achieves the highest detection rate among unassisted methods (85.7% at +-3) and the lowest close-range time (4.8 steps), outperforming an Oracle (5.3 steps). Analysis shows hidden-state update magnitude increases by 17x at regime switches and decays over roughly 10 timesteps, while the discretization step converges to a near-constant value (Delta_t approx 0.78), indicating sensitivity driven by learned dynamics rather than input-dependent gating. Cross-domain experiments in Overcooked show complementary roles of causal attention and prediction-error signals. UA-TOM introduces 7.4 ms inference overhead (14.8% of a 50 ms control budget), enabling reliable regime-switch detection without modifying the base policy.