Pith. sign in

REVIEW 6 cited by

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.07484 v2 pith:7EH3HZOV submitted 2024-10-09 cs.AI

classification cs.AI
keywords worldllmsruleswall-eonlyagentsenvironmentlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Can large language models (LLMs) directly serve as powerful world models for model-based agents? While the gaps between the prior knowledge of LLMs and the specified environment's dynamics do exist, our study reveals that the gaps can be bridged by aligning an LLM with its deployed environment and such "world alignment" can be efficiently achieved by rule learning on LLMs. Given the rich prior knowledge of LLMs, only a few additional rules suffice to align LLM predictions with the specified environment dynamics. To this end, we propose a neurosymbolic approach to learn these rules gradient-free through LLMs, by inducing, updating, and pruning rules based on comparisons of agent-explored trajectories and world model predictions. The resulting world model is composed of the LLM and the learned rules. Our embodied LLM agent "WALL-E" is built upon model-predictive control (MPC). By optimizing look-ahead actions based on the precise world model, MPC significantly improves exploration and learning efficiency. Compared to existing LLM agents, WALL-E's reasoning only requires a few principal rules rather than verbose buffered trajectories being included in the LLM input. On open-world challenges in Minecraft and ALFWorld, WALL-E achieves higher success rates than existing methods, with lower costs on replanning time and the number of tokens used for reasoning. In Minecraft, WALL-E exceeds baselines by 15-30% in success rate while costing 8-20 fewer replanning rounds and only 60-80% of tokens. In ALFWorld, its success rate surges to a new record high of 95% only after 6 iterations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    GILP trains a parameterized backbone for valid actions and state predictions, then uses a consistency gate with LLM drafts to reduce hallucinated-state rate from 0.176 to 0.035 on GPT-4o-mini while raising success fro...

  2. Object-Centric Environment Modeling for Agentic Tasks

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Object-Centric Environment Modeling (OCM) builds an online executable object-and-procedure code model that improves average rank and cuts invalid actions on ScienceWorld, ALFWorld, and PlanCraft.

  3. Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions

    cs.AI 2025-11 conditional novelty 6.0 of 10

    MAPs is a new amusement-park simulator benchmark on which frontier LLM agents score 7–15% of human performance, exposing persistent gaps in long-horizon planning, active learning, spatial reasoning, and handling stoch...

  4. Agent-Environment Alignment via Automated Interface Generation

    cs.AI 2025-05 conditional novelty 6.0 of 10

    ALIGN automatically generates and verifies an interface wrapper that enriches environment observations, improving LLM agent success rates by up to 45.67 percentage points on ALFWorld without modifying the agent or env...

  5. MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems

    cs.AI 2025-08 reject novelty 4.0 of 10

    The authors claim their MultiFluxAI orchestration framework achieves 95% accuracy and 0-10 ms responses by combining rule-based routing, caching, and graph knowledge stores for multi-service RAG queries.

  6. Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges

    cs.LG 2025-08 conditional novelty 4.0 of 10

    A survey reviewing how world models and agentic AI could be combined to give edge devices predictive, proactive decision-making, with a taxonomy of methods, applications, and challenges.

Pith tools