Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis

TL;DR

Caesar is an innovative web exploration agent that constructs a dynamic knowledge graph to facilitate creative synthesis, outperforming existing agents in generating novel insights and answers.

Contribution

The paper introduces Caesar, a deep agentic architecture combining web traversal and adversarial synthesis to enhance creative idea generation.

Findings

Achieves 13% to 23% improvement over state-of-the-art agents in creative synthesis.

Constructs a dynamic knowledge graph for guided exploration of the web.

Demonstrates high novelty and structural coherence in generated artifacts.

Abstract

To advance from passive retrieval to creative discovery of new ideas, autonomous agents must be capable of deep, associative synthesis. However, current agentic frameworks prioritize convergent search, often resulting in derivative summaries that lack creativity. Caesar is an agentic architecture designed to bridge the gap between information gathering and synthesis of new insights. Unlike existing agents that treat the web as a flat sequence of disconnected documents, Caesar performs a deep web traversal to construct a dynamic knowledge graph. This graph then serves as a navigational scaffold, guiding the agent to diverse, non-obvious information that flat retrieval would never encounter. Caesar thus consists of two components: (1) exploration driven by a dynamic context-aware policy that maximizes information coverage across the web's topological structure, and (2) synthesis through adversarial refinement that actively seeks novel perspectives rather than confirming established priors. Caesar demonstrates the ability to generate artifacts and answers characterized by high novelty and structural coherence, achieving 13% to 23% improvement over state-of-the-art deep research agents in creative synthesis challenges, with strong dominance across all output formats.