Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL

• URL: http://arxiv.org/abs/2607.16591v1
• Date: Sat, 18 Jul 2026 02:17:45 GMT
• Title: Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL
• Abstract summary: We instantiate this position in safe model-based control and distil it into three concrete design principles.<n> replacing the model-internal proxy with three world-feedback signals reduces collisions to 1-14% without retraining the world model or the planner.
• Score: 3.556355987197792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The RLxF programme argues that learning signals should come from world feedback rather than from internal model proxies. We instantiate this position in safe model-based control and distil it into three concrete design principles. Empirically, across four world-model architectures spanning a 2x MSE range, MPC planning is statistically equivalent (TOST, n=200), and dynamics-based uncertainty penalties increase collision rates from 26% to 34%: the standard MBRL safety proxy is anti-correlated with safety in this regime. Replacing the model-internal proxy with three world-feedback signals (a sensor-derived margin via minimum lidar, a temporal signal via time-to-collision, and an outcome-supervised feedback model g_psi trained on prior collision labels, structurally analogous to outcome-trained reward models in RLHF) reduces collisions to 1-14% without retraining the world model or the planner. The mechanism is structural: model uncertainty has support over state-prediction space, whereas task risk has support over constraint boundaries, with empirical correlation r < 0.15. From this we extract three RLxF principles (ground risk in world outcomes, validate proxies before deployment, and substitute outcome-trained feedback models when direct world signals are unavailable) and argue they apply equally to model-based control and to verifier-based or RLHF approaches in LLM alignment.

Related papers

• Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs [52.129885179495226]
  This study systematically explores the merging behavior of RL-trained large language models (LLMs) compared to those trained with traditional SFT.<n>We find that RL significantly reduces task conflicts and results in less performance degradation after merging.
  arXiv  Detail & Related papers  (2026-07-24T07:08:57Z)
• Self-Evolving World Models for LLM Agent Planning [72.99782619992361]
  We introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen.<n>WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate.
  arXiv  Detail & Related papers  (2026-06-29T17:58:43Z)
• PROWL: Prioritized Regret-Driven Optimization for World Model Learning [20.10187986360715]
  We introduce a KL-constrained adversarial curriculum in which a policy is trained to expose high-error trajectories of a diffusion-based world model.<n>We implement our approach in the MineRL framework and evaluate it on held-out out-of-distribution trajectories.
  arXiv  Detail & Related papers  (2026-05-11T14:24:19Z)
• Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL [0.8546394944138487]
  We formalize text-based world modeling as a steerable transition-dynamics problem decomposed into initial state.<n>We curate 239,403 grounded state-action trajectories spanning nine open-source environments and twelve frontier model families.<n>We introduce a plug-and-play GRPO training framework with deterministic state checks, and perform zero-shot transfer ablations on three OOD environments.
  arXiv  Detail & Related papers  (2026-05-07T00:40:32Z)
• FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning [16.871281029100313]
  FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC)<n>RCC exposes the system to adversarial participants launching Targeted Label-Flipping Attacks (TLFAs)<n>We propose FedTrident, which can effectively thwart TLFAs, achieving performance comparable to that in attack-free scenarios.
  arXiv  Detail & Related papers  (2026-03-19T16:26:13Z)
• Response-Aware Risk-Constrained Control Barrier Function With Application to Vehicles [0.0]
  This paper proposes a unified control framework based on Response-Aware Risk-Constrained Control Barrier Function for dynamic safety boundary control of vehicles.<n>The framework fuses nominal dynamics priors with direct vehicle body responses to provide a baseline direction for control gradients.<n>It also reformulates traditional deterministic safety constraints into probabilistic constraints on the tail risk of barrier function derivatives.
  arXiv  Detail & Related papers  (2026-03-13T02:38:17Z)
• AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models [75.214287449744]
  We introduce a framework for post-training policy refinement built around an Impartial World Model.<n>Our primary contribution is to teach this model to be honest about danger.<n>We demonstrate through extensive experiments, that our model significantly outperforms baselines in predicting failures.
  arXiv  Detail & Related papers  (2025-11-25T13:57:24Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator [50.191655141020505]
  Reinforcement Learning (RL) has demonstrated impressive capabilities in robotic control but remains challenging due to high sample complexity, safety concerns, and the sim-to-real gap.<n>We introduce Offline Robotic World Model (RWM-O), a model-based approach that explicitly estimates uncertainty to improve policy learning without reliance on a physics simulator.
  arXiv  Detail & Related papers  (2025-04-23T12:58:15Z)
• SafeAMC: Adversarial training for robust modulation recognition models [53.391095789289736]
  In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. These models have been shown to be susceptible to adversarial perturbations, namely imperceptible additive noise crafted to induce misclassification. We propose to use adversarial training, which consists of fine-tuning the model with adversarial perturbations, to increase the robustness of automatic modulation recognition models.
  arXiv  Detail & Related papers  (2021-05-28T11:29:04Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.