Copertina

Equilibrium Residuals Expose Three Regimes of Matrix-Game Strategic Reasoning in Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nie, Wenhua, Luo, Binhan, Meng, Zijie, Jang, Jyh-Shing Roger, Ma, Ching-Wen
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Identified-Set Geometry of Distributional Model Extraction under Top-$K$ Censored API Access
di: Nie, Wenhua, et al.
Pubblicazione: (2026)

The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits
di: Nie, Wenhua, et al.
Pubblicazione: (2026)

Future Validity is the Missing Statistic: From Impossibility to $Φ$-Estimation for Grammar-Faithful Speculative Decoding
di: Nie, Wenhua, et al.
Pubblicazione: (2026)

Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
di: Nie, Wenhua, et al.
Pubblicazione: (2026)

Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
di: Liao, Yen-Lun, et al.
Pubblicazione: (2022)

BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment
di: Hsu, Chih-Hsiang, et al.
Pubblicazione: (2024)

Improving Location-based Thermal Emission Side-Channel Analysis Using Iterative Transfer Learning
di: Lou, Tun-Chieh, et al.
Pubblicazione: (2024)

Residual Prior-driven Frequency-aware Network for Image Fusion
di: Zheng, Guan, et al.
Pubblicazione: (2025)

Self-Training Large Language Models with Confident Reasoning
di: Jang, Hyosoon, et al.
Pubblicazione: (2025)

Improving Real-Time Music Accompaniment Separation with MMDenseNet
di: Wang, Chun-Hsiang, et al.
Pubblicazione: (2024)

Dynamical Regimes of Multimodal Diffusion Models
di: Albrychiewicz, Emil, et al.
Pubblicazione: (2026)

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
di: Guan, Tong, et al.
Pubblicazione: (2025)

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
di: O'Neill, Charles, et al.
Pubblicazione: (2025)

Paths to Equilibrium in Games
di: Yongacoglu, Bora, et al.
Pubblicazione: (2024)

Residual Matrix Transformers: Scaling the Size of the Residual Stream
di: Mak, Brian, et al.
Pubblicazione: (2025)

Towards Generalized Source Tracing for Codec-Based Deepfake Speech
di: Chen, Xuanjun, et al.
Pubblicazione: (2025)

CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
di: Li, Cheng-Yen, et al.
Pubblicazione: (2026)

Doubly Robust Estimation of Causal Effects in Strategic Equilibrium Systems
di: Xiao, Sibo
Pubblicazione: (2025)

Stability and Generalization for Bellman Residuals
di: Kang, Enoch H., et al.
Pubblicazione: (2025)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
di: Duan, Jinhao, et al.
Pubblicazione: (2024)

The Deep Equilibrium Algorithmic Reasoner
di: Georgiev, Dobrik, et al.
Pubblicazione: (2024)

Deep Equilibrium Algorithmic Reasoning
di: Georgiev, Dobrik, et al.
Pubblicazione: (2024)

Building Decision Making Models Through Language Model Regime
di: Zhang, Yu, et al.
Pubblicazione: (2024)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
di: Wang, Kai, et al.
Pubblicazione: (2025)

Research on Metro Transportation Flow Prediction Based on the STL-GRU Combined Model
di: Zhou, Zijie, et al.
Pubblicazione: (2025)

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
di: Xu, Zelai, et al.
Pubblicazione: (2023)

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
di: Jia, Jingru, et al.
Pubblicazione: (2025)

Singer separation for karaoke content generation
di: Lin, Hsuan-Yu, et al.
Pubblicazione: (2021)

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
di: Huang, Benhao, et al.
Pubblicazione: (2026)

From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary
di: Zheng, Qirui, et al.
Pubblicazione: (2025)

Matrix Completion via Residual Spectral Matching
di: Chen, Ziyuan, et al.
Pubblicazione: (2024)

Singing Voice Graph Modeling for SingFake Detection
di: Chen, Xuanjun, et al.
Pubblicazione: (2024)

The Three Regimes of Offline-to-Online Reinforcement Learning
di: Li, Lu, et al.
Pubblicazione: (2025)

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
di: Cai, Yang, et al.
Pubblicazione: (2024)

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
di: Meng, Haoqian, et al.
Pubblicazione: (2026)

A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
di: Nie, Chengyi, et al.
Pubblicazione: (2026)

Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
di: Wei, Xiukun, et al.
Pubblicazione: (2026)

GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
di: Shadarevian, Vartan, et al.
Pubblicazione: (2026)

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
di: Liu, Jincheng, et al.
Pubblicazione: (2025)