Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
Sok: Agentic retrieval-augmented generation (rag): Taxon- omy, architectures, evaluation, and research directions,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
Query decomposition improves structured DevOps retrieval but degrades multi-hop ranking on MuSiQue, while reflection boosts citation accuracy at high latency cost, supporting selective rather than uniform agentic enhancements.
The study applies Bayesian uncertainty propagation to agentic RAG pipelines on StrategyQA and HotpotQA, reporting better discrimination on HotpotQA than on StrategyQA using standard calibration and selective-prediction metrics.
citing papers explorer
-
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Introduces CHARM framework that detects cascading hallucinations in agentic RAG at 89.4% rate with 5.3% false positives and reduces error propagation by 82.1% on multi-hop QA benchmarks.
-
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
Query decomposition improves structured DevOps retrieval but degrades multi-hop ranking on MuSiQue, while reflection boosts citation accuracy at high latency cost, supporting selective rather than uniform agentic enhancements.
-
Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering
The study applies Bayesian uncertainty propagation to agentic RAG pipelines on StrategyQA and HotpotQA, reporting better discrimination on HotpotQA than on StrategyQA using standard calibration and selective-prediction metrics.