arXiv AI

A Qualitative Model for Reasoning about Path and Support

The paper presents a hybrid qualitative model for the block‑puzzle game Camelot Jr., where players must build stable multi‑level bridges to connect two avatars on separate towers. It combines qualitative reasoning with a mathematical center‑of‑mass stability logic to handle the game’s precise physics. The model aims to provide human‑like, explainable guidance that supports spatial skill training in children.

arXiv AI

Sep 17

Clueing up LLMs with Tool-Augmented Deductive Reasoning

The paper introduces a text-based, multi-agent version of the board game Clue to test multi-step deductive reasoning in large language models (LLMs). Six LLM-based agents (GPT‑4o‑mini and Gemini‑2.5‑Flash) play turn‑based games, and a tool‑augmented approach uses a structured possibility matrix to convert implicit game state into explicit remaining possibilities, thereby offloading memory and deductive constraints from the agents. The study compares this tool‑augmented method against a baseline to assess its impact on reasoning quality and task success in a strategic reasoning environment.

By Rebecca Ansell, Autumn Toney-Wails

llms agents

arXiv AI

Sep 10

Compiling VGDL into Causal Models

arXiv:2609.05459v1 Announce Type: new Abstract: Reinforcement learning and large language models often struggle to accurately capture the causal mechanics of game environments. Standard reinforcement...

By Mohit Jiwatode, Bodo Rosenhahn, Alexander Dockhorn

llms agents reinforcement-learning safety

arXiv AI

Oct 7

Towards the Automatic Synthesis of Interpretable Chess Tactics

The paper presents a symbolic sub‑policy model for chess that incorporates domain knowledge to improve interpretability. By adapting patterns learned through inductive logic programming (PAL), the authors evaluate the model using a divergence metric against a random baseline and show that it can suggest moves comparable to a human beginner. They also propose a computational evaluation scheme that augments an existing engine with their model.

By Abhijeet Krishnan, Chris Martens

agents reinforcement-learning benchmarks safety

arXiv AI

Jul 28

Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning

arXiv:2607. 22732v1 Announce Type: new Abstract: LLM-based game agents often perform poorly on more complex tasks.

By Mohit Jiwatode, Ronja Fuchs, Robin Schm\"ocker, Bodo Rosenhahn, Alexander Dockhorn

llms agents benchmarks

arXiv AI

Aug 11

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

arXiv:2503. 19990v4 Announce Type: replace Abstract: Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential steps.

By Kexian Tang, Junyao Gao, Yanhong Zeng, Haodong Duan, Yanan Sun, Zhening Xing, Wenran Liu, Kai Chen, Kaifeng Lyu

llms agents diffusion robotics multimodal benchmarks

arXiv AI

Oct 7

Learning Explainable Representations of Complex Game-playing Strategies

The paper proposes a method that mimics human cognition to train reinforcement learning agents to generate explainable strategies and policies as executable procedures derived from sequences of gameplay actions. It demonstrates automatic learning of such programs for chess and a grid‑based environment, showing that the resulting strategies produce effective actions and can be learned from gameplay data.

By Abhijeet Krishnan, Colin M. Potts, Arnav Jhala, Harshad Khadilkar, Shirish Karande, Chris Martens

agents reinforcement-learning

arXiv Machine Learning

Jul 27

LeAct: Learning to Reason from Expert Actions

arXiv:2607. 21856v1 Announce Type: new Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs.

By Ziran Yang, Chengshuai Shi, Raj Ghugare, Benjamin Eysenbach, Karthik Narasimhan, Chi Jin

llms robotics benchmarks

arXiv AI

Jul 7

ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization

arXiv:2607. 05185v1 Announce Type: new Abstract: Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence.

By Mahnoor Shahid, Hannes Rothe

rag agents benchmarks

arXiv AI

Jun 11

SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning

arXiv:2606. 11770v1 Announce Type: new Abstract: Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions.

By Chao Lei, Yanbei Jiang, Markus Hiller, Zhijian Zhou, Xunye Tian, Krista A. Ehinger, Nir Lipovetzky

llms reinforcement-learning multimodal benchmarks

Hugging Face Trending Papers

Oct 6

Learning Explainable Representations of Complex Game-playing Strategies

As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules to improve their performance. These concepts ar...

agents reinforcement-learning

arXiv Computer Vision

Oct 27

H-GRPO: Permutation-Invariant Reinforcement Learning for Improving Spatial Grounded Reasoning

arXiv:2606.29915v2 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong performance on visual reasoning tasks, yet a correct final answer does not necessarily imply tha...

By Eric Peh, Debaditya Roy, Chen Li, Basura Fernando

llms reinforcement-learning multimodal

arXiv AI

Sep 15

Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help

arXiv:2609.13718v1 Announce Type: cross Abstract: AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open chal...

By Jiahong Li, Sai Siddartha Maram, Atieh Kashani, Ulia Zaman, Zhiyu Lin, Cameron Marano, Roger Azevedo, Jichen Zhu, Magy Seif El-Nasr

llms rag agents

Related stories