AGENTIC-SYSTEMSJune 2, 20261 min read7 views

MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution

At the NeurIPS 2025 MindGames Arena, the In2AI solution utilizing delayed per-step reward attribution won first place in both the Open and Efficient tracks. Remarkably, their 8-billion-parameter open-source model matched or outperformed much larger proprietary systems, including GPT-5.

Computer Science > Artificial Intelligence

Title:MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution

View PDF HTML (experimental)Abstract:Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players. Standard reinforcement learning assumes that rewards can be assigned at each step, but this assumption fails in settings where outcomes are entangled across time and agents. We introduce delayed per-step reward attribution with eligibility gating, an episode lifecycle and postprocessing pipeline that computes rewards only at episode end, propagates them back to originating steps according to task-specific semantics, and excludes steps that lack valid dependent information from training. Together with asynchronous rollout generation via vLLM's continuous batching, curriculum-based opponent sampling, and multi-level stratified batch construction, this approach enables stable, sample-efficient RL training in multi-agent environments. We evaluate on the MindGames Arena benchmark at NeurIPS 2025, where a single 8-billion-parameter open-source model trained with our method matched or surpassed substantially larger proprietary systems, including GPT-5, in head-to-head play and took first place in both the Open (unrestricted) and Efficient (<=8B parameters) tracks.

Current browse context:

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs

HG-RAG (Hierarchy-Guided Retrieval-Augmented Generation) is a novel framework designed to overcome the limitations of traditional flat RAG systems by traversing hierarchical knowledge graphs, significantly improving multi-hop reasoning and reducing hallucinations in LLMs.

agentic-systems

Enhancing Small Language Models Reasoning through Knowledge Graph Grounding

Researchers have proposed a neuro-symbolic framework that enhances the reasoning capabilities of Small Language Models (SLMs) like Gemma 3 and Llama 3.2 using Knowledge Graphs, achieving up to a 2x performance boost.

agentic-systems

Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers

This paper explores how Agentic AI and Model Context Protocol (MCP) can support power-grid studies by integrating LLMs with numerical simulation tools under human supervision.

agentic-systems

Human AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach

Researchers propose a new methodology using Large Language Models and AI agents to construct Bayesian Belief Networks, bridging the gap between expert opinion and data-driven learning. The framework is demonstrated through a healthcare decision-making model, revealing key insights into customer behavior.

agentic-systems

Interpretable Language Model for Closed-Loop Type 1 Diabetes Control

Researchers have developed LLM-T1D, a novel approach combining reinforcement learning and large language models to automate insulin delivery for Type 1 Diabetes. The system not only outperforms traditional methods but also explains its decisions in plain language, addressing the 'black-box' challenge in medical AI.

agentic-systems

RegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics

Researchers have introduced RegNetAgents, an AI-oriented multi-agent framework designed to identify regulatory driver candidates across heterogeneous gene networks in cancer genomics. By integrating bulk tumor and single-cell data, the system offers a powerful tool for discovering therapeutic targets in breast and colorectal cancers.