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

arXiv: https://arxiv.org/abs/2509.06436 · HTML: https://mlsanity.com/paper/2509.06436/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 8 of 8)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [How to Train Long-Context Language Models (Effectively)](https://mlsanity.com/paper/2410.02660/) (2024)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [LongReward: Improving Long-context Large Language Models with AI Feedback](https://mlsanity.com/paper/2410.21252/) (2024)

## Built on by (most cited first, 2 of 2)

- [Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning](https://mlsanity.com/paper/2601.10306/) (2026)
- [Storyline Trees: Hierarchical Representations for Long-Form Narratives](https://mlsanity.com/paper/2606.20900/) (2026)

## Abstract (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.