HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
15 Preprint
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Retrieval-state lock-in causes zero-dispersion errors in 42% of KG-RAG and 59% of dense-retrieval failures; a three-object check rule reaches 91.9% pooled precision at 7.7% coverage.
SAAS applies RL with boundary modeling via rollout contrasts, boundary-aware rewards, and staged optimization to reduce over-search in agentic LLMs while preserving accuracy.
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.
citing papers explorer
-
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
-
When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG
Retrieval-state lock-in causes zero-dispersion errors in 42% of KG-RAG and 59% of dense-retrieval failures; a three-object check rule reaches 91.9% pooled precision at 7.7% coverage.
-
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
SAAS applies RL with boundary modeling via rollout contrasts, boundary-aware rewards, and staged optimization to reduce over-search in agentic LLMs while preserving accuracy.
-
Hybrid Adversarial Defence for Natural Language Understanding Tasks
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.