Skip to content

FloydNet: A Learning Paradigm for Global Relational Reasoning

Jan 2026 · arXiv.org · Vol abs/2601.19094 · 1 citation · 80 references
Computer Science

TL;DR

Under atomic tuple initialization and invariant readout, it is shown that \kfnet{k} is no more graph-discriminative than k-FWL; on BREC, each evaluated variant matches the success set of its corresponding WL reference.

Abstract

Learning algorithmic computation often requires explicit relational intermediate states, yet many graph processors maintain their primary states on individual entities. We introduce \fnet and \textbf{Pivotal Attention} (PA), which maintain ordered pair states and update a target relation $(i,k)$ by attending over candidates formed from $(i,j)$ and $(j,k)$ for every pivot $j$. Motivated by the pair-and-pivot structure of Floyd--Warshall, PA learns relation composition and pivot weighting in parallel rather than executing its ordered min-plus recurrence. The \kfnet{k} framework extends this operation to ordered $k$-tuples, with Self-Attention and PA as its $k=1$ and $k=2$ cases at the attention-operation level. Under atomic tuple initialization and invariant readout, we show that \kfnet{k} is no more graph-discriminative than k-FWL; on BREC, each evaluated variant matches the success set of its corresponding WL reference. \fnet further achieves 96.64\% mean accuracy under the reported CLRS-30 protocol and a 99.8\% optimality rate with 10 samples on held-out non-metric TSP instances.

View source

Similar papers

#artificial intelligence Preprint Aug 2026

Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents

The framework extracts each conversational turn into typed nodes and attributed edges, answers questions from a two-hop subgraph, and periodically prunes nodes that score low on a weighted combination of recency, access frequency, degree centrality, and age.

Theo Rusu, S. Khanzadeh, Manar H. Alalfi · 3 citations · ⚡1
#artificial intelligence Preprint Sep 2026

Externalized CPDAG Summaries Improve LLM Causal Deduction

The results of Corr2Cause support a bounded design principle: externalize the latent object that defines the label, constrain its form, and test whether downstream answers use it.

Wen-Tao Sun, João Paulo Nogueira, Dominique Verchere et al. · 0 citations

RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States

The RunningTensor is introduced, which generalizes this memory to an order-o tensor, updated by a rank-1 outer product and read by contracting against $o-1$ vector queries, and improves performance on language-understanding and non-synthetic retrieval tasks, suggesting that higher-order recurrent state can provide usef...

Luca Herranz-Celotti, Vincent Guigue · 1 citation
Preprint Aug 2026

Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval

This work proposes query-difficulty-gated fusion of reasoning views, a fused ranking that uses no relevance labels at inference, no re-ranking, and no fine-tuning of the retriever; the gate is trained leave-one-task-out.

J. Holdcroft, Abdelrahman Abdallah, Adam Jatowt · 0 citations

Before Answering: Evidence Sufficiency under Size-Matched Memory Construction

Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for this task usually create insufficient-evidence examples by deleting supporting passages. We show that this construction leaks the label through memory size: on MuSiQue,...

Joyanta J. Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik et al. · 1 citation

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.