Graph Search Based Planning With Hierarchical Exploration

via “multi-stage query planning and decomposition”

Autonomous agent for comprehensive research reports.

Unique: Uses a dedicated planner agent with context compression to intelligently decompose queries into parallel sub-queries, rather than simple keyword expansion or fixed templates. The three-tier LLM strategy allows different models for planning vs execution, optimizing cost and latency.

vs others: More intelligent than keyword-based query expansion (e.g., Perplexity's approach) because it uses reasoning to identify conceptual gaps; faster than sequential search because parallelization reduces wall-clock time despite planning overhead.

via “graph search-based planning with hierarchical exploration”

Agent S: an open agentic framework that uses computers like a human

Unique: Implements classical graph search planning combined with LMM-based heuristics for node evaluation, enabling systematic exploration of action sequences with backtracking capabilities rather than greedy single-step decision making

vs others: Provides more systematic exploration than greedy agents through graph search, though at higher computational cost; enables recovery from dead-end paths through backtracking

via “recursive web crawling for hierarchical mapping”

Crawl websites recursively to build a hierarchical map of pages. Convert HTML into clean, LLM-ready Markdown while stripping boilerplate. Accelerate research, grounding, and retrieval workflows with high-quality web context.

Unique: Employs a depth-first search strategy combined with intelligent link extraction to maintain context and state, which is not common in simpler scrapers.

vs others: More efficient than traditional scrapers that only follow links without maintaining a hierarchical context.