# FedWorld: Scope-Aware Federation of Agent World Models

arXiv: https://arxiv.org/abs/2608.01561 · HTML: https://mlsanity.com/paper/2608.01561/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 1 of its 30 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 1 of 1)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)

## Built on by (most cited first, 2 of 2)

- [Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents](https://mlsanity.com/paper/2609.32511/) (2026)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents learn world dynamics from local interaction experience to support subsequent planning and action selection. However, the experience available to a single client is often incomplete, which motivates sharing knowledge across clients. Existing federated methods mainly aggregate model parameters, while agent memory-sharing methods commonly pool trajectories, memories, or rules without checking whether they remain valid for each client. This assumption is problematic because the same abstract action may produce different effects under different policies, environments, or exception conditions. Consequently, a rule supported by most clients may overwrite correct knowledge held by a minority client. To address this problem, we propose FEDWORLD, a scope-aware federated world-model protocol that exchanges structured abstract transition rules. Each client converts private transitions into normalized rules, and the server aligns related rules to identify each rule supporting and contradicting evidence across clients. The resulting evidence determines whether a rule is shared, cluster-specific, private, or unresolved. Each target client retains its local rules and accepts federated updates only for uncovered cases whose inferred scope is compatible; ambiguous rules are withheld. Experiments on τ-bench and ALFWorld show that FEDWORLD reduces negative transfer under conflicting dynamics while retaining useful cross-client transfer, leading to fewer state regressions, repeated actions, and excess steps, as well as higher task success.