SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Presynthesis constructs a tree automaton and oracle offline to allow efficient use of fine-grained abstract semantics for pruning in search-based program synthesis.
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
citing papers explorer
-
SEVerA: Verified Synthesis of Self-Evolving Agents
SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
-
Presynthesis: Towards Scaling Up Program Synthesis with Finer-Grained Abstract Semantics
Presynthesis constructs a tree automaton and oracle offline to allow efficient use of fine-grained abstract semantics for pruning in search-based program synthesis.
-
MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.