# Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis

arXiv: https://arxiv.org/abs/2607.13602 · HTML: https://mlsanity.com/paper/2607.13602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 15 Jul 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, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [Weakly supervised causal representation learning](https://mlsanity.com/paper/2203.16437/) (2022)
- [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Large Language Models as Analogical Reasoners](https://mlsanity.com/paper/2310.01714/) (2023)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [Multi-View Causal Representation Learning with Partial Observability](https://mlsanity.com/paper/2311.04056/) (2023)
- [FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction](https://mlsanity.com/paper/2508.11987/) (2025)
- [A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications](https://mlsanity.com/paper/2506.12594/) (2025)
- [Early science acceleration experiments with GPT-5](https://mlsanity.com/paper/2511.16072/) (2025)
- [Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models](https://mlsanity.com/paper/2310.03965/) (2023)
- [StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding](https://mlsanity.com/paper/2310.12874/) (2023)
- [ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base](https://mlsanity.com/paper/2305.05994/) (2023)
- [MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks](https://mlsanity.com/paper/2602.22808/) (2026)
- [AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies](https://mlsanity.com/paper/2402.12370/) (2024)
- [Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction](https://mlsanity.com/paper/2503.03666/) (2025)
- [ARN: Analogical Reasoning on Narratives](https://mlsanity.com/paper/2310.00996/) (2023)
- [Past Meets Present: Creating Historical Analogy with Large Language Models](https://mlsanity.com/paper/2409.14820/) (2024)

## Abstract (arXiv)

Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the most powerful tools for foresight analysis. In this work, we present a new task called Analogical Deep Research (ADR) to Large Language Model (LLM) agents and construct the first ADR benchmark ADR-bench to study whether LLM agents are able to find and leverage historical analogies when doing foresight analysis. Our investigation reveals a key obstacle: LLM agents are poor at finding analogies because they match on surface features rather than underlying mechanisms. We argue that ADR is inherently a causal question as it requires understanding why the event occurred. Based on our theoretical analysis, we propose two principles required for ADR, including the mechanism alignment and cross-analogy confirmation. Built upon our theoretical results, we propose a new agentic framework called Causal Analogical Researcher (CANA) that guides LLMs to find and integrate historical analogies. CANA incorporates a simple yet effective structural decomposition representation, and integrates structural feedback for reflective improvements of historical analogy identification and integration. We show that CANA brings up to 10% improvements in historical analogy generation, and surpasses the state-of-the-art deep research agents in the ADR-bench. Case studies with the ongoing events confirm the effectiveness of CANA in leveraging historical analogies.