# Controllable Sim Agents with Behavior Latents

Source: [Controllable Sim Agents with Behavior Latents](<https://www.sota2.com/research/paper/6a47421a143ebdcacacc5e39>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-04T05:12:22.129Z

Authors: Juanwu Lu, Junyu Zhu, Ziran Wang

Published: 2026-07-02T17:55:39.000Z

## Abstract

Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enables engineers to isolate variables, reproduce specific edge cases, and test autonomous systems without real-world risk. We introduce Controllable Neural Variational Agents (CNeVA), a controllable simulated-agent framework that learns to infer a per-agent Gaussian behavior latent from per-channel discounted returns via a closed-form conjugate variational update, conditioning a rectified-flow trajectory generator trained on a mixed channel-mask curriculum for classifier-free guidance. To tackle scarcity in reward signals, we propose soft eligibility gates that replace hard binary thresholds with smooth exponential decay, preserving the gradient signal for near-threshold agents. On the Waymo Open Motion Dataset, CNeVA attains competitive realism on the benchmark while exposing per-channel controllability that the higher-ranked imitation models lack. Speed- and acceleration-based steering produces monotone responses without stall-induced reward hacking. Safety controllability is monotone and substantial with the introduction of soft eligibility. We manage to achieve steerable map compliance under a context-residual return measure. Furthermore, our experiment demonstrates that steering metrics must be read alongside physical-plausibility guardrails to avoid reward-hacking confounds.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Traffic Simulation Realism on Waymo Open Motion Dataset (WOMD) 2025 challenge (test)](<https://www.sota2.com/research/sota/traffic-simulation-realism-on-waymo-open-motion-dataset-womd-2025-challenge-test.md>): Traffic Simulation Realism; Waymo Open Motion Dataset (WOMD) 2025 challenge (test); Kinematic Score: 0.4732.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.02496>)

[PDF](<https://arxiv.org/pdf/2607.02496.pdf>)