Foundation World Models For Agents That Learn, Verify, And Adapt Reliably Beyond Static Environments

Abstract

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which limits world models' ability to support agents that must evolve their policies as conditions change. This paper outlines a vision for foundation world models: persistent, compositional representations that unify reinforcement learning, reactive/program synthesis, and abstraction mechanisms. We propose an agenda built around four components: (i) learnable reward models from specifications to support optimization with clear objectives; (ii) adaptive formal verification integrated throughout learning; (iii) online abstraction calibration to quantify the reliability of the model's predictions; and (iv) test-time synthesis and world-model generation guided by verifiers. Together, these components enable agents to synthesize verifiable programs, derive new poli

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydelgrange2026foundation

Related papers

• General Agents Contain World Models (2025)0.00
• Benchmarking World-model Learning (2025)1.57
• World Models As An Intermediary Between Agents And The Real World (2026)0.00
• Active World Model Learning With Progress Curiosity (2020)0.00
• Robust Agents In Open-ended Worlds (2025)0.00
• Imagine-then-plan: Agent Learning From Adaptive Lookahead With World Models (2026)0.00
• Recurrent World Models Facilitate Policy Evolution (2018)0.00
• Object-centric World Models For Causality-aware Reinforcement Learning (2025)0.00