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.
Self-refine: Iter- ative refinement with self-feedback
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
D³ETOR combines debate-enhanced pseudo labeling from SAM with frequency-aware progressive debiasing in FADeNet to achieve state-of-the-art weakly-supervised camouflaged object detection using scribbles.
SRICL combines semantic retrieval from ESCO, in-context learning, fine-tuning, and output verification to achieve higher STRICT-F1 scores and fewer invalid or hallucinated skill spans than GPT-3.5 baselines on six public job-ad datasets.
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
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.
-
Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
D³ETOR combines debate-enhanced pseudo labeling from SAM with frequency-aware progressive debiasing in FADeNet to achieve state-of-the-art weakly-supervised camouflaged object detection using scribbles.
-
Job Skill Extraction via LLM-Centric Multi-Module Framework
SRICL combines semantic retrieval from ESCO, in-context learning, fine-tuning, and output verification to achieve higher STRICT-F1 scores and fewer invalid or hallucinated skill spans than GPT-3.5 baselines on six public job-ad datasets.
-
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.