Cover Image

Towards Understanding Specification Gaming in Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nishimura-Gasparian, Kei, McCarthy, Robert, Lindner, David
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Early Signs of Steganographic Capabilities in Frontier LLMs
by: Zolkowski, Artur, et al.
Published: (2025)

Reasoning Models Struggle to Control their Chains of Thought
by: Yueh-Han, Chen, et al.
Published: (2026)

MISR: Measuring Instrumental Self-Reasoning in Frontier Models
by: Fronsdal, Kai, et al.
Published: (2024)

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
by: Zolkowski, Artur, et al.
Published: (2025)

Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI
by: Rosenfeld, Katherine A., et al.
Published: (2024)

Evaluating and Understanding Scheming Propensity in LLM Agents
by: Hopman, Mia, et al.
Published: (2026)

Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
by: McCarthy, James, et al.
Published: (2025)

Compositional Understanding in Signaling Games
by: Freeborn, David Peter Wallis
Published: (2025)

Towards Understanding the Cognitive Habits of Large Reasoning Models
by: Dong, Jianshuo, et al.
Published: (2025)

A CMOS Probabilistic Computing Chip With In-situ hardware Aware Learning
by: Jhonsa, Jinesh, et al.
Published: (2025)

Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks
by: Maeda, Kiyosu, et al.
Published: (2026)

Toward Modeling Player-Specific Chess Behaviors
by: Sogliuzzo, Loris, et al.
Published: (2026)

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
by: Liao, Yi, et al.
Published: (2025)

Recontextualization Mitigates Specification Gaming without Modifying the Specification
by: Azarbal, Ariana, et al.
Published: (2025)

Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis
by: Jia, Haoyu, et al.
Published: (2026)

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games
by: Piedrahita, David Guzman, et al.
Published: (2025)

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
by: Chen, Danchun, et al.
Published: (2026)

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
by: Minegishi, Gouki, et al.
Published: (2025)

Toward the Axiomatization of Intelligence: Structure, Time, and Existence
by: Itoh, Kei
Published: (2025)

The Token Games: Evaluating Language Model Reasoning with Puzzle Duels
by: Henniger, Simon, et al.
Published: (2026)

Large language models can learn and generalize steganographic chain-of-thought under process supervision
by: Skaf, Joey, et al.
Published: (2025)

Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
by: Duan, Zenghao, et al.
Published: (2026)

Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
by: Huang, Fan, et al.
Published: (2026)

Applying Natural Language Processing and Hierarchical Machine Learning Approaches to Text Difficulty Classification
by: Balyan, Renu, et al.
Published: (2020)

Applying Natural Language Processing and Hierarchical Machine Learning Approaches to Text Difficulty Classification
by: Balyan, Renu, et al.
Published: (2020)

Game On: Towards Language Models as RL Experimenters
by: Zhang, Jingwei, et al.
Published: (2024)

Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games
by: Yang, Yunhao, et al.
Published: (2024)

CreativeGame:Toward Mechanic-Aware Creative Game Generation
by: Ma, Hongnan, et al.
Published: (2026)

Solving a Stackelberg Game on Transportation Networks in a Dynamic Crime Scenario: A Mixed Approach on Multi-Layer Networks
by: Samanta, Sukanya, et al.
Published: (2024)

Enhance Reasoning for Large Language Models in the Game Werewolf
by: Wu, Shuang, et al.
Published: (2024)

Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
by: He, Yidong, et al.
Published: (2026)

Improving Rationality in the Reasoning Process of Language Models through Self-playing Game
by: Wang, Pinzheng, et al.
Published: (2025)

Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games
by: Su, Chris, et al.
Published: (2025)

Ludax: A GPU-Accelerated Domain Specific Language for Board Games
by: Todd, Graham, et al.
Published: (2025)

Internalizing Safety Understanding in Large Reasoning Models via Verification
by: Zhang, Yi, et al.
Published: (2026)

The Geometry of Self-Verification in a Task-Specific Reasoning Model
by: Lee, Andrew, et al.
Published: (2025)

Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games
by: Fan, Mingyuan, et al.
Published: (2026)

HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
by: Liang, Jingcong, et al.
Published: (2025)

Respiratory Inhaler Sound Event Classification Using Self-Supervised Learning
by: Panah, Davoud Shariat, et al.
Published: (2025)

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
by: Xu, Chenhui, et al.
Published: (2025)