WORC improves multi-agent LLM reasoning to 82.2% average accuracy by predicting and compensating for the weakest agent via targeted extra sampling rather than uniform reinforcement.
Rethinking the bounds of llm reasoning: Are multi-agent discussions the key?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AstroVLM deploys expert multi-agent collaboration with VLMs to outperform baselines on real-world astronomical imaging quality diagnosis.
citing papers explorer
-
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
WORC improves multi-agent LLM reasoning to 82.2% average accuracy by predicting and compensating for the weakest agent via targeted extra sampling rather than uniform reinforcement.
-
AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis
AstroVLM deploys expert multi-agent collaboration with VLMs to outperform baselines on real-world astronomical imaging quality diagnosis.