Imagen de Portada

Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yen, Howard, Paranjape, Ashwin, Xia, Mengzhou, Venkatesh, Thejas, Hessel, Jack, Chen, Danqi, Zhang, Yuhao
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
por: Hallinan, Skyler, et al.
Publicado: (2026)

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
por: Lee, Yoonsang, et al.
Publicado: (2026)

Long-Context Language Modeling with Parallel Context Encoding
por: Yen, Howard, et al.
Publicado: (2024)

How to Train Long-Context Language Models (Effectively)
por: Gao, Tianyu, et al.
Publicado: (2024)

DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models
por: Ye, Xi, et al.
Publicado: (2026)

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
por: Zhang, Wuwei, et al.
Publicado: (2025)

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
por: Weller, Orion, et al.
Publicado: (2024)

SimPO: Simple Preference Optimization with a Reference-Free Reward
por: Meng, Yu, et al.
Publicado: (2024)

LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
por: Ye, Xi, et al.
Publicado: (2025)

Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training
por: Zhong, Zexuan, et al.
Publicado: (2024)

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
por: Xia, Mengzhou, et al.
Publicado: (2023)

LitSearch: A Retrieval Benchmark for Scientific Literature Search
por: Ajith, Anirudh, et al.
Publicado: (2024)

HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
por: Yen, Howard, et al.
Publicado: (2024)

Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
por: Luo, Hongyin, et al.
Publicado: (2025)

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
por: Chen, Qianben, et al.
Publicado: (2026)

LESS: Selecting Influential Data for Targeted Instruction Tuning
por: Xia, Mengzhou, et al.
Publicado: (2024)

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
por: Zhu, Xinyu, et al.
Publicado: (2025)

Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion
por: Lan, Tian, et al.
Publicado: (2026)

ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
por: Wu, Xixi, et al.
Publicado: (2025)

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

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
por: Wu, Jinyang, et al.
Publicado: (2026)

Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
por: Wang, Ante, et al.
Publicado: (2025)

Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
por: Bhaskar, Adithya, et al.
Publicado: (2025)

Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
por: Kamath, Amita, et al.
Publicado: (2026)

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
por: Gao, Jiaxuan, et al.
Publicado: (2025)

Precise Information Control in Long-Form Text Generation
por: He, Jacqueline, et al.
Publicado: (2025)

Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention
por: Zhan, Zhihao, et al.
Publicado: (2025)

BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning
por: Zhao, Yubao, et al.
Publicado: (2026)

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
por: Chen, Howard, et al.
Publicado: (2025)

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
por: Li, Junjie, et al.
Publicado: (2026)

Context as a Tool: Context Management for Long-Horizon SWE-Agents
por: Liu, Shukai, et al.
Publicado: (2025)

Detecting Pretraining Data from Large Language Models
por: Shi, Weijia, et al.
Publicado: (2023)

Continual Memorization of Factoids in Language Models
por: Chen, Howard, et al.
Publicado: (2024)

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
por: Zhang, Yinger, et al.
Publicado: (2026)

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
por: Lumer, Elias, et al.
Publicado: (2026)

MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
por: Ye, Juexiang, et al.
Publicado: (2026)

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
por: Li, Mufei, et al.
Publicado: (2025)

OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
por: Li, Jinze, et al.
Publicado: (2026)

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
por: Kalyan, Vivek, et al.
Publicado: (2025)

CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
por: Wang, Zirui, et al.
Publicado: (2024)