# Solving Context Window Overflow in AI Agents

arXiv: https://arxiv.org/abs/2511.22729 · HTML: https://mlsanity.com/paper/2511.22729/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 7 of 7)

- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases](https://mlsanity.com/paper/2410.14594/) (2024)
- [LongFuncEval: Measuring the effectiveness of long context models for function calling](https://mlsanity.com/paper/2505.10570/) (2025)
- [Concise and Precise Context Compression for Tool-Using Language Models](https://mlsanity.com/paper/2407.02043/) (2024)
- [EcoAct: Economic Agent Determines When to Register What Action](https://mlsanity.com/paper/2411.01643/) (2024)

## Built on by (most cited first, 4 of 4)

- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [View-oriented Conversation Compiler for Agent Trace Analysis](https://mlsanity.com/paper/2603.29678/) (2026)
- [On Problems of Implicit Context Compression for Software Engineering Agents](https://mlsanity.com/paper/2605.11051/) (2026)
- [SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch](https://mlsanity.com/paper/2607.27167/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and Materials Science. However, large tool outputs can overflow the LLMs' context window, preventing task completion. Existing solutions such as truncation or summarization fail to preserve complete outputs, making them unsuitable for workflows requiring the full data. This work introduces a method that enables LLMs to process and utilize tool responses of arbitrary length without loss of information. By shifting the model's interaction from raw data to memory pointers, the method preserves tool functionality, allows seamless integration into agentic workflows, and reduces token usage and execution time. The proposed method is validated on a real-world Materials Science application that cannot be executed with conventional workflows, and its effectiveness is demonstrated via a comparative analysis where both methods succeed. In this experiment, the proposed approach consumed approximately seven times fewer tokens than the traditional workflow.