Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on S2-Bench.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.
citing papers explorer
-
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on S2-Bench.
-
Characterizing Model-Native Skills
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
-
Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.