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

• URL: http://arxiv.org/abs/2606.00017v1
• Date: Mon, 13 Apr 2026 23:59:03 GMT
• Title: MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution
• Abstract summary: Training language model agents for multi-agent strategic interaction presents a core difficulty.<n>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.<n>We introduce delayed per-step reward attribution with eligibility gating, an episode lifecycle and postprocessing pipeline.
• Score: 45.957713330643934
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning [50.464623632604976]
  In this work, we study RL-based training of vision-language models (VLMs) for long-horizon decision-making in Super Mario Land.<n>We propose an adapted variant of PPO with a lightweight turn-level critic, which substantially improves training stability and sample efficiency.<n>We introduce Odysseus, an open training framework for VLM agents, achieving substantial gains across multiple levels of the game.
  arXiv  Detail & Related papers  (2026-05-01T02:05:56Z)
• SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents [0.31034395048547575]
  Existing approaches rely on static prompting strategies or handcrafteds to select actions such as code editing, file navigation, and test execution.<n>We propose SWE-Shepherd, a framework that introduces Process Reward Models (PRMs) to provide dense, step-level supervision for repository-level code agents.<n>Experiments on SWE-Bench Verified demonstrate improved interaction efficiency and action quality, while also highlighting challenges in aligning intermediate rewards with final task success.
  arXiv  Detail & Related papers  (2026-04-12T06:51:47Z)
• ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking [84.07076200941474]
  ArenaRL is a reinforcement learning paradigm that shifts from pointwise scalar scoring to intra-group relative ranking.<n>We construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals.<n>Experiments show that ArenaRL substantially outperforms standard RL baselines.
  arXiv  Detail & Related papers  (2026-01-10T08:43:07Z)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning [30.44007644340425]
  We introduce PROPA, a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations.<n>Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines.<n>It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art.
  arXiv  Detail & Related papers  (2025-11-13T13:06:12Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games [42.74003740156243]
  We address the problem of agile 1v1 quadrotor pursuit-evasion, where a pursuer and an evader learn to outmaneuver each other.<n>We propose an Asynchronous Multi-Stage Population-Based (AMSPB) algorithm to tackle these issues.<n>Within this framework, we train neural network controllers that output either velocity commands or body rates with collective thrust.
  arXiv  Detail & Related papers  (2025-06-03T13:19:23Z)
• Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark [72.46357004059661]
  Generalist Virtual Agents (GVAs) have shown significant promise in autonomous task execution.<n>To address these challenges, we propose Similar, a Step-Wise Multi-Dimensional Generalist Reward Model.<n>Similar offers fine-grained signals for agent training and can choose better action for inference-time scaling.
  arXiv  Detail & Related papers  (2025-03-24T13:30:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.