HFEPX Hub
Updated from current HFEPX corpus (Feb 27, 2026). 12 papers are grouped in this hub page. Common evaluation modes: Simulation Env, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Freeform. Frequently cited benchmark: Lawbench. Common metric signal: cost. Newest paper in this set is from Feb 24, 2026.
Updated from current HFEPX corpus (Feb 27, 2026). This page covers 12 papers centered on Simulation Env + Multi Agent Papers. Common evaluation modes include Simulation Env, Llm As Judge, with benchmark emphasis on Lawbench, Visualwebarena. Use the anchored takeaways below to compare protocol choices and identify papers with stronger evidence depth.
Evaluation emphasis: Simulation Env and Llm As Judge appear frequently in this slice.
Evidence: Cooperative-Competitive Team Play of Real-World Craft Robots , Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence , MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation
Benchmark concentration: Lawbench, Visualwebarena helps control cross-paper variance.
Evidence: Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence , MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation , World-Model-Augmented Web Agents with Action Correction
Metric concentration: cost, success rate is repeatedly reported in this group.
Evidence: MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation , World-Model-Augmented Web Agents with Action Correction , Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
Evidence: World-Model-Augmented Web Agents with Action Correction , Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems , Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
Stratify by benchmark (Lawbench vs Visualwebarena) before comparing methods.
Evidence: Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems , Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook , OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
Papers with explicit human feedback is visible in approximately 16.7% of papers in this set.
Evidence: Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook , OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery , Multimodal Multi-Agent Empowered Legal Judgment Prediction
Papers with explicit human feedback
Coverage is a replication risk (16.7% vs 45% target).
Papers reporting quality controls
Coverage is a replication risk (0% vs 30% target).
Papers naming benchmarks/datasets
Coverage is a replication risk (16.7% vs 35% target).
Papers naming evaluation metrics
Coverage is a replication risk (8.3% vs 35% target).
Papers with known rater population
Coverage is a replication risk (16.7% vs 35% target).
Papers with known annotation unit
Coverage is a replication risk (8.3% vs 35% target).
1. Cooperative-Competitive Team Play of Real-World Craft Robots
Start with this anchor paper for scope and protocol framing. Covers Simulation Env.
2. Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence
Covers Simulation Env.
3. MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation
Covers Simulation Env.
4. World-Model-Augmented Web Agents with Action Correction
Covers Llm As Judge, Simulation Env.
5. Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Covers Simulation Env.
6. Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
Covers Simulation Env.
7. OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
Covers Simulation Env.
8. Multimodal Multi-Agent Empowered Legal Judgment Prediction
Covers Simulation Env.
simulation_env vs llm_as_judge
both=2, left_only=10, right_only=0
2 papers use both Simulation Env and Llm As Judge.
Rui Zhao, Xihui Li, Yizheng Zhang, Yuzhen Liu, Zhong Zhang · Feb 24, 2026 · Citations: 0
Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years.
ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao · Feb 24, 2026 · Citations: 0
The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or optimizing prompt engi
Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani · Feb 18, 2026 · Citations: 0
MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation.
Zhouzhou Shen, Xueyu Hu, Xiyun Li, Tianqing Fang, Juncheng Li · Feb 17, 2026 · Citations: 0
Web agents based on large language models have demonstrated promising capability in automating web tasks.
Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud · Feb 16, 2026 · Citations: 0
Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks.
Ming Li, Xirui Li, Tianyi Zhou · Feb 15, 2026 · Citations: 0
As large language model agents increasingly populate networked environments, a fundamental question arises: do artificial intelligence (AI) agent societies undergo convergence dynamics similar to human social systems?
Qi Liu, Ruochen Hao, Can Li, Wanjing Ma · Feb 14, 2026 · Citations: 0
We present OR-Agent, a configurable multi-agent research framework designed for automated exploration in rich experimental environments.
Zhaolu Kang, Junhao Gong, Qingxi Chen, Hao Zhang, Jiaxin Liu · Jan 19, 2026 · Citations: 0
Furthermore, we build JurisMM, a large dataset with over 100,000 recent Chinese judicial records, including both text and multimodal video-text data, enabling comprehensive evaluation.
Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka · Oct 20, 2025 · Citations: 0
Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable.
Mohammad Hossein Samaei, Faryad Darabi Sahneh, Lee W. Cohnstaedt, Caterina Scoglio · Sep 24, 2025 · Citations: 0
We introduce EpidemIQs, a novel multi-agent LLM framework that integrates user inputs and autonomously conducts literature review, analytical derivation, network modeling, mechanistic modeling, stochastic simulations, data visualization and
Florian Lehmann, Krystsina Shauchenka, Daniel Buschek · Sep 15, 2025 · Citations: 0
We propose integrating AI agents directly into collaborative writing environments.
M. Saifullah, K. G. Papakonstantinou, A. Bhattacharya, S. M. Stoffels, C. P. Andriotis · Jan 23, 2024 · Citations: 0
To tackle the high dimensionality of state and action spaces, we propose DDMAC-CTDE, a Deep Decentralized Multi-Agent Actor-Critic (DDMAC) reinforcement learning architecture with Centralized Training and Decentralized Execution (CTDE).
