# Question's Gambit changes the first retrieval step for deep research agents

The one-time method splits a question into clues, runs complementary searches, and reranks the pooled results before the agent loop starts. On BrowseComp-Plus, with the same retriever and agent loop, GPT-5.5 rises from 83.1% to 90.5%.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:32:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/a0db9ade3c8c44b3b746c89f.html

Content language: en
Localization state: sameLanguage

Source: elvis · Published 9/22/2026, 07:53:20

Question's Gambit runs once before a deep research agent starts searching. It splits the question into clues, turns each clue into complementary searches, pools the results, and reranks them so the agent begins with that ranked set already in context. The paper is [Question's Gambit (arXiv:2609.14412)](https://arxiv.org/abs/2609.14412).

With the same retriever and the same agent loop, the change moves BrowseComp-Plus accuracy from 83.1% to 90.5% for GPT-5.5, from 68.1% to 79.0% for GPT-5.4-mini, and from 71.4% to 76.9% for DeepSeek-v4-pro. It roughly halves calibration error for GPT-5.5 and adds 2.3 to 5.3 tool calls per question. elvis describes the gain as coming from this opening context.

In an error analysis of the remaining GPT-5.5 mistakes, only 3 of 79 come from the gold document never being retrieved. The other 76 occur later, when the agent previews, opens, or uses the evidence.

Tags: Question's Gambit, Deep research, BrowseComp-Plus, Retrieval

[View original post](https://x.com/omarsar0/status/2102171057612566585)