Image de couverture de livre

LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pushkin, Denys, Abbe, Emmanuel
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
par: Pushkin, Denys, et autres
Publié: (2024)

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
par: Mahrooghi, Ilia, et autres
Publié: (2026)

Breaking the Context Bottleneck on Long Time Series Forecasting
par: Ma, Chao, et autres
Publié: (2024)

AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
par: Gao, Silin, et autres
Publié: (2025)

How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
par: Abbe, Emmanuel, et autres
Publié: (2024)

$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture
par: Brilliantov, Kirill, et autres
Publié: (2026)

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
par: Zhou, Yang, et autres
Publié: (2025)

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
par: Wang, Xinyu Jessica, et autres
Publié: (2026)

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
par: Xu, Baixuan, et autres
Publié: (2025)

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
par: Motwani, Sumeet Ramesh, et autres
Publié: (2026)

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
par: Wang, Tianyi, et autres
Publié: (2026)

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
par: Hu, Yuyang, et autres
Publié: (2026)

RL for Reasoning by Adaptively Revealing Rationales
par: Amani, Mohammad Hossein, et autres
Publié: (2025)

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
par: Wei, Songtao, et autres
Publié: (2026)

The Illusion of Procedural Reasoning: Measuring Long-Horizon FSM Execution in LLMs
par: Samiei, Mahdi, et autres
Publié: (2025)

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
par: Liu, Yuxin, et autres
Publié: (2026)

Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution
par: Liao, Hsien-Jyh
Publié: (2026)

SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models
par: Monti, Sebastiano, et autres
Publié: (2026)

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
par: Shi, Yaorui, et autres
Publié: (2026)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
par: Wan, Guangya, et autres
Publié: (2025)

Revisiting LLM Reasoning via Information Bottleneck
par: Lei, Shiye, et autres
Publié: (2025)

When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
par: Li, Chen, et autres
Publié: (2026)

HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds
par: Anokhin, Petr, et autres
Publié: (2025)

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
par: Wang, Tianle, et autres
Publié: (2026)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
par: Yang, Zhicheng, et autres
Publié: (2026)

Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
par: Saegert, Paul, et autres
Publié: (2026)

Towards Reasonable Concept Bottleneck Models
par: Kalampalikis, Nektarios, et autres
Publié: (2025)

Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling
par: Cao, Shijie, et autres
Publié: (2026)

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs
par: Vaghasiya, Jay, et autres
Publié: (2025)

SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
par: Tang, Chenwei, et autres
Publié: (2025)

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

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
par: Hu, Yuyang, et autres
Publié: (2026)

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
par: Cheng, Zelei, et autres
Publié: (2024)

HorizonBench: Long-Horizon Personalization with Evolving Preferences
par: Li, Shuyue Stella, et autres
Publié: (2026)

From Differentiation to Cognition: UTD as a Model of Recursive Awareness
par: Spirin, Denys
Publié: (2025)

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
par: Liu, Jinkun, et autres
Publié: (2026)

SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
par: Kariyappa, Sanjay, et autres
Publié: (2026)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
par: Zhang, Zijing, et autres
Publié: (2025)

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
par: Wang, Zihao, et autres
Publié: (2024)

Verifiable Benchmarking of Long-Horizon Spatial Biology
par: Diks, Ian, et autres
Publié: (2026)