The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, transfer to the broader class of knowledge-intensive, multi-agent LLM applications.
Abstract
Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. This paper presents AutoWorldBuilder, a multi-agent collaborative system that addresses these challenges through five integrated components: a structured concept network with conflict detection; a DAG-based hybrid batch scheduler that groups tasks by semantic locality; a four-layer context compression mechanism achieving approximately 90% token reduction; an iterative review system with specialized Auditor agents that improves proposal pass rates from 42% to over 85%; and a skill-driven agent architecture supporting zero-code extension with differentiated temperature configuration. Two experiments across 20 diverse worldbuilding tasks, using GPT-OSS 120B and DeepSeek v3.2 as LLM backends, demonstrate a 95.0% success rate. The system generated 56-103 self-consistent concepts per world in 18-31 minutes with zero-conflict delivery. The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, transfer to the broader class of knowledge-intensive, multi-agent LLM applications.
Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, and application to realistic, grounded scenarios. To address these concerns, we present WorldBench: a comprehensive, multilingual benchmark of genuine, persona-grounded everyday workflows, where agents can act in a sandbox via structured actions. WorldBench comprises 1,600 tasks across seven languages and eight cultures, filtered and refined through feedback from human annotators with language- and culture-specific expertise. For evaluation, we extend metrics from previous works and introduce Constrained Task Success (CTS), which combines natural language instructions and testbeds to score task completion, minimal modification, and other complementary metrics through deterministic and LLM-as-a-Judge evaluations. Our experiments show that frontier models reach only 49.2% CTS, with all models demonstrating large gaps between correctness and environment preservation. We thereby show that current agents remain brittle in multilingual, agentic scenarios, especially for long-horizon tasks and under state-preservation constraints
Leonardo Ranaldi, Sherrie Shen, Jushi Kai et al.· 0 citations
LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in many important domains like game playing and robotics, the strongest available agents are not language models. Integrating non-language agents with LLMs would require \emph{verbalization}: compressing their rich continuous representations into sparse textual summaries at each interaction step. To study whether verbalization constitutes a bottleneck, we introduce \textsc{LLAMIA-Bench}, a suite of six diverse collaborative chess tasks spanning three facets: behavioral imitation, state assessment, and natural-language explanation. Each task instantiates a well-established chess problem that neither the LLM nor the chess engine can solve alone. To solve LLM collaboration with non-language agents, we introduce \emph{latent state internalization}, which projects the subagent's continuous representations directly into the LLM's token stream as learned state tokens, with dynamic re-encoding as actions advance the environment state. Comparing internalization to verbalized integration, our experiments reveal a consistent \emph{verbalization debt}: the performance gap widens throughout training and persists as the LLM scales from 4B to 14B parameters. A single 14B model, \textsc{LLAMIA}, trained with latent state internalization, matches or exceeds task specialists and frontier models including GPT-5.1 with tool access across all benchmark tasks, and generalizes out-of-distribution where task-specific finetunes collapse
A scalable Agentic GraphRAG architecture structured under a comprehensive LLMOps Feature-Extraction-Inference (FTI) lifecycle, which achieves a 70% improvement in Citation Rate compared to standard Vector RAG and establishes a robust Safe Abstention rate, effectively mitigating the risk of ungrounded generation.
Marcelo Massashi Simonae, A. Ortoncelli, Marlon Marcon· International Conference on...· 0 citations
PhoenixRepair is a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, thereby expanding the search space of repair strategies and achieves higher fault localization accuracy than existing approaches.
Tian-Yue Jiang, Yan-Lin Wang, Xin He et al.· arXiv.org· 2 citations
AgentRadio is presented, an asynchronous message-passing layer that equips coding-agent harnesses with three primitives: threads, messages, and waiting for mentions that shows the gain growing with task difficulty, consistent with mid-course correction as the underlying mechanism.
Xinxing Ren, Qianbo Zang, Ziyan Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
