mlsanityData to 7 Oct 2026

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

arXiv 2410.10584 ↗First posted 14 Oct 2024cs.AI cs.LG cs.MAcited by 4

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. STACKFEED defines a ReACT actor agent on each document to perform structured edits based on document specific targeted instructions. Experimental results showcase that STACKFEED significantly improves KB quality and performance of the RAG system. We evaluate STACKFEED on low-resource programming problems, modified python packaged and factual question-answering tasks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 49 of its 84 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

49 of 84 references.

References · 49

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  6. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  10. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  11. 2022Mass-Editing Memory in a Transformercited by 976
  12. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
37 more
  1. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  2. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  4. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  5. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  6. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  7. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  8. 2021Editing Factual Knowledge in Language Modelscited by 548
  9. 2022Memory-Based Model Editing at Scalecited by 443
  10. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  11. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  12. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  13. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  14. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  15. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
  16. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  17. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
  18. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  19. 2024LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMscited by 142
  20. 2021Lifelong Pretraining: Continually Adapting Language Models to Emerging Corporacited by 114
  21. 2020Off-Policy Multi-Agent Decomposed Policy Gradientscited by 97
  22. 2024LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigationcited by 92
  23. 2023MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAcited by 80
  24. 2017Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learningcited by 70
  25. 2023Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledgecited by 66
  26. 2023Propagating Knowledge Updates to LMs Through Distillationcited by 28
  27. 2024Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Taskscited by 24
  28. 2023KILM: Knowledge Injection into Encoder-Decoder Language Modelscited by 19
  29. 2024MetaReflection: Learning Instructions for Language Agents using Past Reflectionscited by 19
  30. 2024Task Facet Learning: A Structured Approach to Prompt Optimizationcited by 17
  31. 2024LOGIC-LM++: Multi-Step Refinement for Symbolic Formulationscited by 14
  32. 2023Retrieval-augmented Multilingual Knowledge Editingcited by 13
  33. 2023Cross-Lingual Knowledge Editing in Large Language Modelscited by 11
  34. 2024Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loopcited by 10
  35. 2024CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patientscited by 9
  36. 2024Language Modeling with Editable External Knowledgecited by 9
  37. 2022Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradientcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  2. 2025Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agentscited by 4
  3. 2025Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledgecited by 3
  4. 2025Memorization and Knowledge Injection in Gated LLMscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization
  2. 2025SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
  3. 2026CRITIC-R1: Learning Structured Critics for Retrieval-Augmented Generation
  4. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
  5. 2025SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation
  6. 2025KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
  7. 2025Multi-hop Reasoning via Early Knowledge Alignment
  8. 2026EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation