paper-with-me

홈 › Papers

Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning

2025-09-08 · Song Yu, Xiaofei Xu, Ke Deng, Li Li, Lin Tian arxiv

Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the lost in the middle issue, where information located in the middle of a long input tends to be underutilized. Some existing methods that reduce input have the risk of discarding key information, while others that extend context windows often lead to attention dispersion. To address these limitations, we propose Tree of Agents (TOA), a multi-agent reasoning framework that segments the input into chunks processed by independent agents. Each agent generates its local cognition, then agents dynamically exchange information for collaborative reasoning along tree-structured paths. TOA enables agents to probe different reasoning orders for multi-perspective understanding, effectively mitigating position bias and reducing hallucinations. To improve processing efficiency, we incorporate prefix-hash caching and adaptive pruning strategies, achieving significant performance improvements with comparable API overhead. Experiments show that TOA, powered by compact LLaMA3.1-8B, significantly outperforms multiple baselines and demonstrates comparable performance to the latest and much larger commercial models, such as Gemini1.5-pro, on various long-context tasks. Code is available at https://github.com/Aireduce952/Tree-of-Agents.

📄 PDF Abstract BibTeX arXiv:2509.06436

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents

2026-03-10 · Naman Gupta, Vaibhav Singh, Arun Iyer, Kirankumar Shiragur 외 arxiv

Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-based worker agents that read from and up…

Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning

2025-03-10 · Xintong Li, Jalend Bantupalli, Ria Dharmani, Yuwei Zhang 외

There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing long-term open-domain dialogue datasets la…

Retrieval

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

2026-06-18 · Yanxi Chen, Weijie Shi, Yuexiang Xie, Boyi Hu 외 arxiv

This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment,…

Reinforcement LearningDomain Generalization

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering

2025-11-17 · Jielin Qiu, Zuxin Liu, Zhiwei Liu, Rithesh Murthy 외 arxiv

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like LoCoBen…

Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent

2026-04-29 · Zhentao Xu, Shangjin Zhang, Emir Poyraz, Yvonne Li 외 arxiv

Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semant…