Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
3 results for “hypergraph”
Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball
A new hypergraph representation learning framework called MGHRL is introduced to adaptively generate multi-granularity hyperedges using granular-ball splitting, improving high-order relational modeling over prior fixed-definition methods.
Sep 10, 2026
HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents
HyperAgent is a new LLM agent framework that models tool interactions as a hypergraph of input/output schemas to improve planning efficiency and reduce redundant API calls and token usage in complex task execution.
Aug 5, 2026
Reference-Free Evaluation of Reasoning in Open-Ended Question Answering
Researchers introduced a new reference-free framework to audit LLM reasoning traces by decomposing them into segments, labeling premise-target relations via NLI, and organizing those into a hypergraph with deterministic backward search — validated on mathematical and clinical reasoning benchmarks.
Jul 23, 2026