The World State Generator is a model that writes a plan as checkable states of the world and keeps that plan aligned with the world it runs in, a model that raises end-to-end success for two open models near 30B parameters over prompting and brings to the level of proprietary model.
Abstract
Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next decides the task. Prompted planners fail at exactly this point, rewriting the refused step in new words, meeting the same refusal, and burning the attempt budget without moving. They fail because the plan was never tied to the world, so a refusal has nothing in the plan to attach to. A world is where a task runs, and it has its own rules, its own admissible actions, and its own constraints. We build synthetic worlds across 7 domains and extract training data from them. A program enforces each world's rules and grades its goal, and every world is admitted only if its goal is reachable from its initial state. Agents run inside and leave verified failures paired with repairs that carried the run to a state the world certified, a record of about 226K trajectories. On this record we train the World State Generator, a model that writes a plan as checkable states of the world and keeps that plan aligned with the world it runs in. That alignment is what a plan written in language lacks, since the world it runs in has physical limits, logical dependencies, and required orders the language never states, and the plan encounters these rules only when a state fails. WSG takes that failure as the rule the world has stated and rewrites the remaining states to obey it, so the plan bends to the world as the run goes on. Across 7 public benchmarks, WSG raises end-to-end success for two open models near 30B parameters over prompting and brings to the level of proprietary model.
The world agent task is proposed, which moves the evaluation point of world generation from the moment of delivery to the continued operation that follows, and makes the continued operation of a world measurable and distinguishes local completion from failures in event organization.
Wei-Xing Chen, Wei-Peng Zhang, Nan An et al.· arXiv.org· 0 citations
Across three models, two reasoning regimes, and two domains, four findings hold without per-turn reasoning: displaying accurate state is unreliable, an unverified ledger the agent writes itself beats an accurate checklist it is shown, directives help in proportion to the model's obedience, and enforcement needs no obed...
C. Zhang, Wonbin Kweon, Jia-Wei Han· arXiv.org· 0 citations
SAGE (Symbolic Action-Gating and Editing), a single-LLM planner built from two lightweight mechanisms: a domain-agnostic symbolic gate that blocks precondition-violating actions with typed reasons as a runtime safety monitor, and a local edit that regenerates only the failed sub-goal's suffix, keeping completed and unt...
T. Bui, Jongsul Moon, Youngouk Kim et al.· arXiv.org· 0 citations
A novel and scalable framework that rewrites a coding agent's context as the repository changes rather than as the context grows, and can achieve a higher resolve rate in all experiments spanned by six coding agents and three edit-heavy benchmarks with little computational overhead.
These lessons are distill into concrete recommendations for building robot systems that improve themselves, each paired with an experiment that could prove it wrong.
It is shown a proof-of-the-concept lifted planner can sometimes solve the BPP problem by using a domain-independent heuristic that guides search for a plan.