Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
Improving retrieval-augmented generation through multi-agent reinforcement learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.
RioRAG uses nugget-centric verification with cross-source checks to create dense verifiable rewards for RL-based optimization of long-form RAG, yielding higher factual recall and faithfulness on LongFact and RAGChecker.
Proposes five foundational pillars and architectural patterns for building robust GenAI-native systems by combining AI with software engineering principles.
citing papers explorer
-
To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG
Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
-
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
- OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
- Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic