Copertina

Limited Reasoning Space: The cage of long-horizon reasoning in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zhenyu, Wu, Guanlin, Wang, Cheems, Zhao, Yongqiang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Harnessing the power of LLMs for normative reasoning in MASs
di: Savarimuthu, Bastin Tony Roy, et al.
Pubblicazione: (2024)

Exploring System 1 and 2 communication for latent reasoning in LLMs
di: Coda-Forno, Julian, et al.
Pubblicazione: (2025)

Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments
di: Meng, Guanlin
Pubblicazione: (2023)

Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
di: Zhang, Weichen, et al.
Pubblicazione: (2025)

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
di: Zhang, Zhen, et al.
Pubblicazione: (2025)

Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space
di: Yang, Jinrong, et al.
Pubblicazione: (2025)

Autoregressive long-horizon prediction of plasma edge dynamics
di: Csala, Hunor, et al.
Pubblicazione: (2025)

Can LLMs perform structured graph reasoning?
di: Agrawal, Palaash, et al.
Pubblicazione: (2024)

StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
di: Che, Chang, et al.
Pubblicazione: (2026)

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
di: Qu, Yun, et al.
Pubblicazione: (2025)

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
di: Luo, Linhao, et al.
Pubblicazione: (2025)

Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
di: Qu, Yun, et al.
Pubblicazione: (2024)

How well do LLMs reason over tabular data, really?
di: Wolff, Cornelius, et al.
Pubblicazione: (2025)

Are LLMs classical or nonmonotonic reasoners? Lessons from generics
di: Leidinger, Alina, et al.
Pubblicazione: (2024)

Can formal argumentative reasoning enhance LLMs performances?
di: Castagna, Federico, et al.
Pubblicazione: (2024)

MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs
di: Li, Guangyan, et al.
Pubblicazione: (2025)

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
di: Yang, Yuchen, et al.
Pubblicazione: (2024)

The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
di: Jullien, Maël, et al.
Pubblicazione: (2025)

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
di: Gao, Songyang, et al.
Pubblicazione: (2025)

An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project
di: Rasnayaka, Sanka, et al.
Pubblicazione: (2024)

Explore the Reasoning Capability of LLMs in the Chess Testbed
di: Wang, Shu, et al.
Pubblicazione: (2024)

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
di: Cinquin, Tristan, et al.
Pubblicazione: (2025)

QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?
di: Li, Belinda Z., et al.
Pubblicazione: (2025)

Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
di: Feng, Yiyang, et al.
Pubblicazione: (2026)

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

Chain or tree? Re-evaluating complex reasoning from the perspective of a matrix of thought
di: Tang, Fengxiao, et al.
Pubblicazione: (2025)

Zero-Knowledge Audit for Internet of Agents: Privacy-Preserving Communication Verification with Model Context Protocol
di: Jing, Guanlin, et al.
Pubblicazione: (2025)

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
di: Qu, Yun, et al.
Pubblicazione: (2024)

Stepwise Reasoning Error Disruption Attack of LLMs
di: Peng, Jingyu, et al.
Pubblicazione: (2024)

Logos: An evolvable reasoning engine for rational molecular design
di: Wen, Haibin, et al.
Pubblicazione: (2026)

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
di: Zou, Deyu, et al.
Pubblicazione: (2025)

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
di: Wang, Zeyu, et al.
Pubblicazione: (2026)

Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs
di: Yang, Zhuo, et al.
Pubblicazione: (2025)

Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition
di: Li, Guanlin, et al.
Pubblicazione: (2025)

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
di: Zhang, Zheng
Pubblicazione: (2025)

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
di: Kuratov, Yuri, et al.
Pubblicazione: (2024)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
di: Lin, Bill Yuchen, et al.
Pubblicazione: (2025)

Strategy-Aware Optimization Modeling with Reasoning LLMs
di: Zhao, Ruiqing, et al.
Pubblicazione: (2026)