CivBench is an open‑source benchmark that evaluates language‑model agents in the long‑horizon, tool‑mediated game Civilization VI using the Model Context Protocol (MCP). Each episode lasts over 300 turns, generating thousands of tool calls across a 76‑tool action space, and includes a narration layer that translates visual game state into structured text. The study characterises agent behaviour across four model families, introducing Proactive Monitoring Rate (PMR) and RAG@10 as interface‑level metrics, and finds that agents often under‑monitor strategic state and fail to execute near‑term commitments despite tool access and explicit guidance.
arXiv:2610.02563v1 Announce Type: cross Abstract: We present OpenGameEval, a benchmark and evaluation framework for agentic game development inside Roblox Studio. It runs language models as agents in...
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
Kepler is an open‑source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction checks. In the ARC‑AGI‑3 benchmark, a frozen Claude Opus 5 configuration achieved a perfect 100.00 RHAE on all 25 public games without per‑game model selection or score‑conditioned reruns, and matched or outperformed median‑human action counts on 181 of 183 levels. The study also identified three evaluation failures and highlighted that public‑set score alone has limited discriminative value, advocating for first‑attempt, cost‑conditioned, and verification‑aware reporting. whyItMatters":"The results demonstrate that a purely score‑based evaluation can be misleading, underscoring the need for more rigorous, cost‑aware, and verification‑aware metrics in AI benchmark assessments."
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
The paper introduces Gauntlet, a framework that lets large language models autonomously build game-playing agents from a bare contract—just a game description, raw observation/action interface, and an empty policy file. In a single session, the model experiments with the game, compiles a standalone controller, and the resulting program is evaluated on held‑out instances without further model calls. The authors demonstrate that these compiled agents can win full‑scale games such as StarCraft II and Civilization, marking the first time a language‑agent system has achieved standalone victory in such complex titles.
arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
arXiv:2606. 29932v3 Announce Type: replace Abstract: Long-horizon strategic planning in complex strategy games requires coordinating tightly coupled decision domains, including technology, economy, diplomacy, and military, across hundreds of turns under imperfect information.
The paper introduces BRIA (BRanch-Inspect-Adopt), an agent that isolates tool‑candidate investigations into separate branches, executing each candidate independently and then inspecting the execution evidence to adopt only useful results. BRIA dynamically retrieves additional tools as new needs arise during task execution and is evaluated on PlanBench‑XL and MCP‑Atlas with a library of 1,897 tools, outperforming or matching the strongest retrieval baselines. On MCP‑Atlas, BRIA achieves an average claim score of 89.77 versus 75.40 for MCP‑Zero, and it lies on the Pareto frontier for task performance and input‑token cost.
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
Interlock is a framework that transforms long‑horizon tasks into typed completion graphs, linking evidence, decisions, and required effects through grounding, coupling, and realization edges. It compiles these graphs into a resettable workspace, a public request, and an evaluation rubric, and uses source‑coverage, public‑input, and agent‑as‑judge reviews to ensure that all mandatory requirements are met. Fine‑tuning Qwen3.6 backbones on Interlock‑generated trajectories improves pass rates on AutomationBench, JobBench, and Harvey LAB, showing that the synthesized experience benefits external task environments.