Imagen de Portada

Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Liao, Hsien-Jyh
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry
por: Liao, Hsien-Jyh
Publicado: (2026)

The Illusion of Procedural Reasoning: Measuring Long-Horizon FSM Execution in LLMs
por: Samiei, Mahdi, et al.
Publicado: (2025)

Intrinsic Credit Assignment for Long Horizon Interaction
por: Auzina, Ilze Amanda, et al.
Publicado: (2026)

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
por: Sinha, Akshit, et al.
Publicado: (2025)

HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds
por: Anokhin, Petr, et al.
Publicado: (2025)

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks
por: Orimo, Yuki, et al.
Publicado: (2025)

SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
por: Li, Jialiang, et al.
Publicado: (2025)

LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
por: Pushkin, Denys, et al.
Publicado: (2026)

When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
por: Zhu, Zilin, et al.
Publicado: (2026)

Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
por: Deng, Zehao, et al.
Publicado: (2025)

EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
por: Hu, Xavier, et al.
Publicado: (2026)

Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning
por: Hwang, Jaebak, et al.
Publicado: (2025)

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
por: Motwani, Sumeet Ramesh, et al.
Publicado: (2026)

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
por: Wang, Tianyi, et al.
Publicado: (2026)

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
por: Hu, Yuyang, et al.
Publicado: (2026)

Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
por: Wei, Rongzhe, et al.
Publicado: (2026)

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
por: Li, Junlong, et al.
Publicado: (2025)

Environment Maps: Structured Environmental Representations for Long-Horizon Agents
por: Feng, Yenchia, et al.
Publicado: (2026)

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
por: Liu, Yuxin, et al.
Publicado: (2026)

SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models
por: Monti, Sebastiano, et al.
Publicado: (2026)

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
por: Shi, Yaorui, et al.
Publicado: (2026)

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
por: Hu, Chuanrui, et al.
Publicado: (2026)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
por: Wan, Guangya, et al.
Publicado: (2025)

When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
por: Li, Chen, et al.
Publicado: (2026)

DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
por: Yan, Hao, et al.
Publicado: (2026)

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
por: Wang, Tianle, et al.
Publicado: (2026)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
por: Yang, Zhicheng, et al.
Publicado: (2026)

Reasoning with Autoregressive-Diffusion Collaborative Thoughts
por: Yuan, Mu, et al.
Publicado: (2026)

MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
por: Li, Ruoran, et al.
Publicado: (2026)

Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling
por: Cao, Shijie, et al.
Publicado: (2026)

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs
por: Vaghasiya, Jay, et al.
Publicado: (2025)

SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
por: Tang, Chenwei, et al.
Publicado: (2025)

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
por: Huang, Fan
Publicado: (2026)

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
por: Hu, Yuyang, et al.
Publicado: (2026)

HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
por: Wang, Jiacheng, et al.
Publicado: (2026)

Natural Language Edge Labelling: Decoupling Intent from Execution in Structured LM Reasoning
por: Madahar, Abhinav
Publicado: (2025)

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
por: Chen, Xianwei, et al.
Publicado: (2026)

Limits to AI Growth: The Ecological and Social Consequences of Scaling
por: Bhardwaj, Eshta, et al.
Publicado: (2025)

HorizonBench: Long-Horizon Personalization with Evolving Preferences
por: Li, Shuyue Stella, et al.
Publicado: (2026)