Diagnosing and Mitigating Context Rot in Long-horizon Search

arXiv:2606.29718v2 Announce Type: replace-cross Abstract: 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.

Abstract: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.

Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

arXiv:2606.29718 [cs.IR]

(or arXiv:2606.29718v2 [cs.IR] for this version)

https://doi.org/10.48550/arXiv.2606.29718 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Diagnosing and Mitigating Context Rot in Long-horizon Search

Related coverage