# Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery

arXiv: https://arxiv.org/abs/2605.18854 · HTML: https://mlsanity.com/paper/2605.18854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 13 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 15 of 15)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory](https://mlsanity.com/paper/2311.08719/) (2023)
- [CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents](https://mlsanity.com/paper/2511.02734/) (2025)
- [Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2601.06007/) (2026)
- [Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression](https://mlsanity.com/paper/2505.19433/) (2025)
- [AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts](https://mlsanity.com/paper/2601.20730/) (2026)
- [Towards a Standard, Enterprise-Relevant Agentic AI Benchmark: Lessons from 5.5 billion tokens' worth of agentic AI evaluations](https://mlsanity.com/paper/2511.08042/) (2025)
- [Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models](https://mlsanity.com/paper/2601.07978/) (2026)
- [MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models](https://mlsanity.com/paper/2601.11969/) (2026)

## Built on by (most cited first, 1 of 1)

- [Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents](https://mlsanity.com/paper/2608.31057/) (2026)

## Abstract (arXiv)

Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force practitioners to choose between truncation and task failure. While numerous memory condensation strategies have been proposed, from simple sliding windows to LLM-generated summaries, no systematic comparison exists to guide strategy selection, especially in scientific discovery tasks. We evaluate eight memory condensation strategies using GPT-4o on sixty DiscoveryBench tasks spanning six scientific domains (480 total evaluations). We find that no condenser significantly alters hypothesis quality, while LLM-based condensers increase token costs by 24-94 percent, and masking tool-call outputs achieves an 8.6 percent net savings. We also observe that the optimal condenser for data-driven scientific discovery varies by scientific domain and task length.