# Diagnosing and Mitigating Context Rot in Long-horizon Search

arXiv: https://arxiv.org/abs/2606.29718 · HTML: https://mlsanity.com/paper/2606.29718/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [AgentFold: Long-Horizon Web Agents with Proactive Context Management](https://mlsanity.com/paper/2510.24699/) (2025)
- [Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2510.12635/) (2025)
- [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark](https://mlsanity.com/paper/2505.18761/) (2025)
- [The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break](https://mlsanity.com/paper/2604.11978/) (2026)
- [Drift No More? Context Equilibria in Multi-Turn LLM Interactions](https://mlsanity.com/paper/2510.07777/) (2025)
- [FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents](https://mlsanity.com/paper/2510.03204/) (2025)
- [Evaluating Long-Context Reasoning in LLM-Based WebAgents](https://mlsanity.com/paper/2512.04307/) (2025)
- [Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification](https://mlsanity.com/paper/2510.06135/) (2025)
- [Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search](https://mlsanity.com/paper/2510.18939/) (2025)
- [PAACE: A Plan-Aware Automated Agent Context Engineering Framework](https://mlsanity.com/paper/2512.16970/) (2025)

## Built on by (most cited first, 3 of 3)

- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Stateless Language Agents: Scaling Long-Horizon Automated Research](https://mlsanity.com/paper/2610.07625/) (2026)
- [Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help](https://mlsanity.com/paper/2610.06069/) (2026)

## Abstract (arXiv)

Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon search tasks. The concern that increasing context length degrades model capabilities, known as context rot, has become a widely recognized issue for these applications. However, in deep search scenarios, it remains unclear how models actually fail under extensive context, and to what extent existing methods can mitigate such failures. Through a systematic study of four flagship models across three benchmarks, we identify a previously overlooked phenomenon, which we term premature termination: under extensive context, models give up or provide uncertain incorrect answers long before exhausting the context window. By controlling for query difficulty, we show that the premature termination rate is positively correlated with context length. Based on the findings, we revisit methods to mitigate context rot, including context management and parallel sampling. For context management, we analyze seven methods across three categories and show that they are inherently test-time scaling strategies that reduce the premature termination rate to enable more exploration, and we further provide model-dependent principles for method selection. For parallel sampling, we develop a behavior-aware filtering strategy and observe a performance gain of 2.6% to 4.9% across three aggregation methods.