G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a neuro-symbolic approach, ``Guiding with Recurrent Reasoning Models'' (G-RRM), which integrates SE-RRMs with symbolic solvers for constraint satisfaction problems. SE-RRMs act as neural solvers that generate full solution proposals and guide classical symbolic solvers, such as backtracking or SAT-based methods like Glucose 4.1 and CaDiCaL 3.0.0, that produce globally correct solutions. Centrally, we investigate when neural guidance with G-RRM i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorTimo Bertram →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
- Linked via arxiv authorSidhant Bhavnani →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
- Linked via arxiv authorRichard Freinschlag →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
- Linked via arxiv authorErich Kobler →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
- Linked via arxiv authorAndreas Mayr →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
- Linked via arxiv authorGünter Klambauer →
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models