A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
A two-phase non-parametric retrieval workflow that separates high-recall candidate retrieval from high-precision utility ranking with LLM-as-a-Judge scoring for evidence extraction in multilingual financial documents.
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
MASS-RAG uses distinct agents for evidence summarization, extraction, and reasoning, then synthesizes their outputs to improve answer quality over standard RAG baselines on four benchmarks, especially when evidence is distributed.
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
citing papers explorer
-
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
Capabilities of Gemini Models in Medicine
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
-
Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting
A two-phase non-parametric retrieval workflow that separates high-recall candidate retrieval from high-precision utility ranking with LLM-as-a-Judge scoring for evidence extraction in multilingual financial documents.
-
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
-
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
MASS-RAG uses distinct agents for evidence summarization, extraction, and reasoning, then synthesizes their outputs to improve answer quality over standard RAG baselines on four benchmarks, especially when evidence is distributed.
-
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
- Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning