回顾性世界建模提升VLM智能体推理能力
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
这篇论文提出让VLM智能体不仅能预测未来,还能回溯过去判断因果一致性,解决了物理行为不连贯的问题。
研究人员提出回顾性世界建模(Retrospective World Modeling)新范式,使智能体能反向推理状态转换的因果一致性。
该方法通过估计动作归因分布P(â_t|s_t,s_{t+1}),构建自一致性奖励(SCR)信号。实验表明,该方法在多样化智能体任务中显著提升了策略的鲁棒性和泛化能力,优于仅依赖前瞻性预测的基线模型。
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dependence of policy learning on costly real-world interactions. Existing methods mainly rely on prospective simulation to predict the consequences of candidate actions. However, this forward-only paradigm focuses on what will happen next and provides limited constraints for verifying whether an action is causally consistent with the observed state transition, which can lead to plausible-looking but physically incoherent behaviors. In this paper, we challenge the view of world modeling as only prospective prediction and introduce Retrospective World Modeling, a new agent learning paradigm that enables agents to reason backward by estimating the retrospective attribution distribution $P(\hat{a}{t}|s_t, s{t+1})$ for the action that most likely caused a given transition. Based on this capability, we formulate the Self-Consistency Reward (SCR), an intrinsic signal that measures the probabilistic consistency between the policy action and the retrospective explanation. Integrating SCR into reinforcement learning provides dense transition-level feedback and steers agents toward behaviors that are both task-effective and physically grounded. Extensive experiments across diverse agentic tasks show that our method substantially improves policy robustness and generalization over prospective-only world modeling baselines.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include VLM, world models, agents, causal inference.
Source attribution: curated from arXiv cs.AI (@Yongjiang Liu, Jie Zhang, Haoyue Zhang, Jingcai Guo, Deze Zeng, Song Guo).