CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-09

Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs

Lorenzo Pantè, Andrea Fanti, Roberto Capobianco

Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills. A major challenge when designing such curricula is assessing task difficulty relative to the agent's current learning progress. While previous work has explored using scalar task scores or textual summaries of the agent's behavior, here we study a different approach: directly inspecting policy behavior via recorded episode videos. We introduce a simple yet effective instantiation of this approach which leverages a Video Language Model (VLM) to both process these videos and provide curriculum recommendations, which we call Visual Inspection of Policies (VIP). Since videos can naturally contain any number of controllable agents, we empirically study VIP on the StarCraft Multi-Agent Challenge (SMAC). We show that even with a lightweight and openly accessible VLM (VideoLLaMa2-7B), VIP can use policy videos to generate more effective curricula than both its text-only ablation and methods that rely on scalar task scores.

View free PDFSource page

Related papers

arxivcs.AIcs.CLcs.LGcs.MA2026-07-07

Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems

Yaowen Ye, Jacob Steinhardt

AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards. This multi-agent competition can lead to behaviors that serve individual gains at collective cost -- for instance, marketing agents may post misleading content as a…

View free PDFSource page
arxivcs.ROcs.AIcs.CVcs.LG2026-07-06

IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction

Honglin Wang, Shiyao Pan, Yun-Fu Liu

Multi-agent motion prediction is essential for automated vehicles to understand the intentions of surrounding vehicles. However, previous prediction-based and anchor-based methods have limitations in mode diversity and prediction accuracy, respectively. These limitations may caus…

View free PDFSource page
arxivcs.CRcs.AIcs.IRcs.LGcs.MA2026-07-08

Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems

Yufei Xia, Anjun Gao, Yueyang Quan, Zhuqing Liu, Minghong Fang

Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures. When an execution fails, identifying which agent is re…

View free PDFSource page
arxivcs.AIcs.CLcs.LG2026-07-12

Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning

Sudipto Ghosh, Tanmoy Chakraborty

Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing…

View free PDFSource page
arxivcs.LGcs.AI2026-07-09

Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning

Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown

As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provid…

View free PDFSource page
arxivcs.ROcs.AIcs.CLcs.LG2026-07-06

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

Kaiyuan Chen, Shuangyu Xie, Letian Fu, Justin Yu, William Pacini, Sandeep Bajamahal, et al.

For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies? We focus on "Variational Automation" (VA), a class of tasks that h…

View free PDFSource page