Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Qianben, Qin, Tianrui, Zhu, King, Wang, Qiexiang, Yu, Chengjun, Xu, Shu, Wu, Jiaqi, Zhang, Jiayu, Liu, Xinpeng, Gui, Xin, Cao, Jingyi, Wang, Piaohong, Shi, Dingfeng, Zhu, He, Wang, Tiannan, Wang, Yuqing, Song, Maojia, Zheng, Tianyu, Zhang, Ge, Yang, Jian, Liu, Jiaheng, Liu, Minghao, Jiang, Yuchen Eleanor, Zhou, Wangchunshu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
di: Yao, Yi, et al.
Pubblicazione: (2026)

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
di: Wang, Piaohong, et al.
Pubblicazione: (2025)

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
di: Li, Weizhen, et al.
Pubblicazione: (2025)

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
di: Chen, Qianben, et al.
Pubblicazione: (2025)

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
di: Qin, Tianrui, et al.
Pubblicazione: (2025)

TaskCraft: Automated Generation of Agentic Tasks
di: Shi, Dingfeng, et al.
Pubblicazione: (2025)

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
di: Gui, Xin, et al.
Pubblicazione: (2025)

SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?
di: Chen, Jiamin, et al.
Pubblicazione: (2026)

How Far Are We from Genuinely Useful Deep Research Agents?
di: Zhang, Dingling, et al.
Pubblicazione: (2025)

Towards Personalized Deep Research: Benchmarks and Evaluations
di: Liang, Yuan, et al.
Pubblicazione: (2025)

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
di: Ding, Dongyi, et al.
Pubblicazione: (2025)

PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
di: Tao, Meiling, et al.
Pubblicazione: (2025)

Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
di: Zhu, Chenghao, et al.
Pubblicazione: (2025)

PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning
di: Liu, Xiaoyou, et al.
Pubblicazione: (2026)

Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search
di: Zhang, Haoyu, et al.
Pubblicazione: (2024)

AI PERSONA: Towards Life-long Personalization of LLMs
di: Wang, Tiannan, et al.
Pubblicazione: (2024)

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

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
di: Wang, Liang, et al.
Pubblicazione: (2026)

OAgents: An Empirical Study of Building Effective Agents
di: Zhu, He, et al.
Pubblicazione: (2025)

An Ensemble of Evolutionary Algorithms With Both Crisscross Search and Sparrow Search for Processing Inferior Individuals
di: Du, Mingxuan, et al.
Pubblicazione: (2026)

Effect of Interfacial Properties on the Agglomeration Characteristics of Inclusions in High‐Manganese and High‐ Aluminum Steels
di: Yuqing Yin, et al.
Pubblicazione: (2025)

SRLAgent: Enhancing Self-Regulated Learning Skills through Gamification and LLM Assistance
di: Ge, Wentao, et al.
Pubblicazione: (2025)

Scaling Test-time Compute for LLM Agents
di: Zhu, King, et al.
Pubblicazione: (2025)

Efficient Agents: Building Effective Agents While Reducing Cost
di: Wang, Ningning, et al.
Pubblicazione: (2025)

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
di: Wang, Zekun Moore, et al.
Pubblicazione: (2024)

OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
di: Liang, Haijian, et al.
Pubblicazione: (2026)

LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
di: Lu, Yijun, et al.
Pubblicazione: (2026)

Large‐Scale Synthesis of High‐Purity Isoguanosine and Resolution of its Crystal Structure by Microcrystal Electron Diffraction
di: Kaichao Wang, et al.
Pubblicazione: (2024)

Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration
di: Li, Haichang, et al.
Pubblicazione: (2026)

Repurposing Synthetic Data for Fine-grained Search Agent Supervision
di: Zhao, Yida, et al.
Pubblicazione: (2025)

DanModCap: Designing a Danmaku Moderation Tool for Video-Sharing Platforms that Leverages Impact Captions with Large Language Models
di: Hu, Siying, et al.
Pubblicazione: (2024)

To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
di: Zhang, Wenlin, et al.
Pubblicazione: (2026)

Regular Tree Search for Simulation Optimization
di: Wang, Du-Yi, et al.
Pubblicazione: (2025)

i-Octree: A Fast, Lightweight, and Dynamic Octree for Proximity Search
di: Zhu, Jun, et al.
Pubblicazione: (2023)

Geometric curvature effect on suppressing the Ion-Temperature-Gradient mode near the magnetic axis
di: Wu, Tiannan, et al.
Pubblicazione: (2025)

CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs
di: Wang, Kangsheng, et al.
Pubblicazione: (2024)

Symbolic Learning Enables Self-Evolving Agents
di: Zhou, Wangchunshu, et al.
Pubblicazione: (2024)

Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks
di: Tang, Keke, et al.
Pubblicazione: (2025)

NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search
di: Qin, Yijian, et al.
Pubblicazione: (2022)

From Random Search to Bandit Learning in Metric Measure Spaces
di: Han, Chuying, et al.
Pubblicazione: (2023)