Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation

• URL: http://arxiv.org/abs/2606.23280v1
• Date: Mon, 22 Jun 2026 12:57:17 GMT
• Title: Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation
• Abstract summary: Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis.<n>Existing approaches based on large language models (LLMs) remain inherently correlation-driven, relying on iterative environmental feedback to refine reward hypotheses for each specific task.<n>We propose the Causal Reward World Model (CRWM), which explicitly models the causal relationships between candidate reward components and task-targeted physical variables through offline pre-training on multi-task interaction data.
• Score: 23.371552518874807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. However, existing approaches based on large language models (LLMs) remain inherently correlation-driven, relying on iterative environmental feedback to refine reward hypotheses for each specific task. This paradigm not only results in inefficient reasoning but also makes LLMs susceptible to semantically plausible yet causally spurious reward components, leading to ineffective optimization. To address these limitations, we propose the Causal Reward World Model (CRWM), which explicitly models the causal topological relationships between candidate reward components and task-targeted physical variables through offline pre-training on multi-task interaction data. Based on a coarse-to-fine pre-training strategy, we introduce a joint optimization module that integrates Explicit Mechanism Decoupling with Confidence-Aware Soft Fusion to refine coarse structural priors using micro-level trajectories, thereby constructing a robust and interpretable causal skeleton. During inference, LLMs leverage CRWM as a task-irrelevant causal prior to constrain the reward generation, enabling zero-shot reward function design. Our work opens up a new white-box paradigm for the ARD problem. Extensive experiments on complex continuous control benchmarks demonstrate that CRWM generates executable reward functions without feedback-driven reward refinement, significantly reducing the design latency for acquiring new robotic skills while matching or surpassing state-of-the-art performance, and further exhibits strong generalization capabilities across unseen tasks and diverse robotic embodiments.

Related papers

• Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making [0.0]
  This paper addresses key technical challenges in current large language model (LLM) agent applications, including long-horizon planning, sparse reward attribution, and dynamic environmental interaction.<n>The proposed architecture is based on the synthesis of core AI paradigms: Visual, Language, Generative, Graph, Multimodal, Reinforcement, and Agent Intelligence.<n>Ultimately, the resulting architecture offers a practical, scalable reference framework for developing artificial intelligence technologies in complex, multi-step autonomous systems.
  arXiv  Detail & Related papers  (2026-07-19T02:51:41Z)
• EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly [12.727917085274841]
  EUPHORIA is a unified framework that achieves universal few-shot adaptability and dynamic efficiency.<n>For structural reasoning, we introduce a Physics-Informed Graph Transformer trained via Soft Actor-Critic.<n>Experiments show that EUPHORIA significantly reduces energy consumption over decoupled baselines.
  arXiv  Detail & Related papers  (2026-05-15T18:25:49Z)
• Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning [57.10440766103372]
  Trajectory Regularized Merging (TRM) is a framework that reformulates the merging phase as an optimization process within an augmented trajectory subspace.<n>Our framework integrates three synergistic objectives including task alignment, prediction consistency, and gradient responsiveness to concurrently preserve merged model's historical stability and re-activate optimization dynamics.
  arXiv  Detail & Related papers  (2026-05-08T14:07:32Z)
• Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning [52.48243762705385]
  Chain of Uncertain Rewards (CoUR) is a novel framework that integrates large language models (LLMs) to streamline reward function design and evaluation.<n>We show that CoUR achieves better performance and significantly lowers the cost of reward evaluations.
  arXiv  Detail & Related papers  (2026-04-15T05:44:14Z)
• ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback [0.0]
  We propose ReVEL: Multi-Turn Reflective LLM-Heuristic Evolution via Structured Performance Feedback.<n>The core of ReVEL lies in two mechanisms: (i) performance-profile grouping and (ii) multi-turn feedback-driven reflection.<n>Our results highlight multi-turn reasoning with structured grouping as a principled paradigm for automated design.
  arXiv  Detail & Related papers  (2026-03-05T04:52:11Z)
• Discovering Process-Outcome Credit in Multi-Step LLM Reasoning [3.584086358722852]
  Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs)<n>We propose a novel framework designed to provide continuous reward signals.<n>Our model exhibits superior out-of-distribution robustness, demonstrating promising zero-shot transfer capabilities to unseen and challenging reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-01T05:44:09Z)
• The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination [0.9099663022952496]
  We argue that recent advances in large language models point toward a shift from hand-crafted numerical rewards to language-based objective specifications.<n>We conceptualize this transition along three dimensions: semantic reward specification, dynamic reward adaptation, and improved alignment with human intent.
  arXiv  Detail & Related papers  (2026-01-13T05:47:18Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models [99.85131798240808]
  We introduce a novel generative framework called textitGuided Topology Diffusion (GTD)<n>Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process.<n>At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards.<n>Experiments show that GTD can generate highly task-adaptive, sparse, and efficient communication topologies.
  arXiv  Detail & Related papers  (2025-10-09T05:28:28Z)
• Uncertainty-aware Reward Design Process [6.013578016233855]
  We propose the Uncertainty-aware Reward Design Process (URDP), a novel framework that integrates large language models to streamline reward function design and evaluation.<n>URDP quantifies candidate reward function uncertainty based on self-consistency analysis, enabling simulation-free identification of ineffective reward components.<n>We conduct a comprehensive evaluation of URDP across 35 diverse tasks spanning three benchmark environments.
  arXiv  Detail & Related papers  (2025-07-03T03:09:17Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

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.