Harmonia: End-to-End RAG Serving Optimization | Paper Citation Record

Observation 0480d2e8-106d-459a-83a8-1f76c17d4325 · outbound

This paper cites https://grpc.io/, 2025.

Harmonia: End-to-End RAG Serving Optimization https://grpc.io/, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.261461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b47cea-c865-4ec5-b17b-3df01f7d7cf0 · outbound

This paper cites Infercept: efficient intercept support for augmented large language model inference.

Harmonia: End-to-End RAG Serving Optimization Infercept: efficient intercept support for augmented large language model inference

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.268066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f9870d-eca0-4bac-92e5-d621a86044b4 · outbound

This paper cites What’s new in gurobi 9.0.

Harmonia: End-to-End RAG Serving Optimization What’s new in gurobi 9.0

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.279508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81f62ec3-5d84-4aed-a8da-f5ebdb970fda · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

Harmonia: End-to-End RAG Serving Optimization SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.288007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 966905e3-01a9-496a-b02c-c43b34009d9e · outbound

This paper cites Programming with legion.

Harmonia: End-to-End RAG Serving Optimization Programming with legion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.296338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe05ce2a-03d6-4103-95a9-b6593c32820c · outbound

This paper cites Improving lan- guage models by retrieving from trillions of tokens.

Harmonia: End-to-End RAG Serving Optimization Improving lan- guage models by retrieving from trillions of tokens

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.303671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bacffb9e-e8fd-49ce-a0d0-32d5ca798013 · outbound

This paper cites RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation.

Harmonia: End-to-End RAG Serving Optimization RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.311048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2868bcf-0928-43e9-abfd-557519f96b81 · outbound

This paper cites Lire: Efficient query rewriting for re- trieval augmented generation systems.

Harmonia: End-to-End RAG Serving Optimization Lire: Efficient query rewriting for re- trieval augmented generation systems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.316474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d16ba18f-498d-40bf-8243-3b66ba97baa3 · outbound

This paper cites an unresolved cited work.

Harmonia: End-to-End RAG Serving Optimization Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.321800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 872d91e7-9d31-43eb-a149-f470a3cc49dc · outbound

This paper cites Xgboost: A scalable tree boosting system.

Harmonia: End-to-End RAG Serving Optimization Xgboost: A scalable tree boosting system

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.328120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b19faf4-2332-440b-a10a-c760c0bdcdaa · outbound

This paper cites HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA.

Harmonia: End-to-End RAG Serving Optimization HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.333272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ff8f5b7-9eca-4e70-9ed2-d8dc9b13b80b · outbound

This paper cites Llm-inference-bench: Inference benchmarking of large language models on ai accelerators.

Harmonia: End-to-End RAG Serving Optimization Llm-inference-bench: Inference benchmarking of large language models on ai accelerators

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.338828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9b0ca4a-0c47-417e-9cf5-d91560a4f9cb · outbound

This paper cites Lazybatching: An sla-aware batching system for cloud machine learning inference, 2020.

Harmonia: End-to-End RAG Serving Optimization Lazybatching: An sla-aware batching system for cloud machine learning inference, 2020

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.508133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d96d695b-04f2-41f9-8688-22f7d57ee945 · outbound

This paper cites https://github.com/ chroma-core/chroma.

Harmonia: End-to-End RAG Serving Optimization https://github.com/ chroma-core/chroma

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.479660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 38586f25-f17a-4230-a053-4f724788060a · outbound

This paper cites Clipper: A{Low-Latency} online prediction serving system.

Harmonia: End-to-End RAG Serving Optimization Clipper: A{Low-Latency} online prediction serving system

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.356160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0df209-7ed1-4cc7-94b0-ea6121bf3731 · outbound

This paper cites Mapreduce: simplified data pro- cessing on large clusters.

Harmonia: End-to-End RAG Serving Optimization Mapreduce: simplified data pro- cessing on large clusters

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.448239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4bfec62a-cd14-45c0-ba84-c0030a34bf4c · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

Harmonia: End-to-End RAG Serving Optimization From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.373824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3d065ee-fdac-4d2e-836d-7755387e1339 · outbound

This paper cites KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation.

Harmonia: End-to-End RAG Serving Optimization KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.380147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3969794f-a71e-47f2-9710-28c2c19b8e6a · outbound

This paper cites T-RAG: Lessons from the LLM Trenches.

Harmonia: End-to-End RAG Serving Optimization T-RAG: Lessons from the LLM Trenches

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.386092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5982065e-aeea-4bbc-85b2-d3b902d91787 · outbound

This paper cites Chainpoll: A high efficacy method for LLM hallucination detection.

Harmonia: End-to-End RAG Serving Optimization Chainpoll: A high efficacy method for LLM hallucination detection

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.394614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd6b6c9-2136-4ace-ab7a-e059cfe4ad25 · outbound

This paper cites Dominant resource fairness: Fair allocation of multiple resource types.

Harmonia: End-to-End RAG Serving Optimization Dominant resource fairness: Fair allocation of multiple resource types

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.429178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 47e8c3fb-8115-4cad-97f5-5259d393d5ad · outbound

This paper cites Serving {DNNs} like clockwork: Performance predictability from the bottom up.

Harmonia: End-to-End RAG Serving Optimization Serving {DNNs} like clockwork: Performance predictability from the bottom up

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.405137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d1e3e448-832b-4a24-8077-a44f5135071a · outbound

This paper cites Accelerating large-scale inference with anisotropic vector quantization.

Harmonia: End-to-End RAG Serving Optimization Accelerating large-scale inference with anisotropic vector quantization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.378009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 601abd6f-0926-434b-b173-0773b9221642 · outbound

This paper cites Hipporag: Neurobiologically inspired long-term memory for large language models.

Harmonia: End-to-End RAG Serving Optimization Hipporag: Neurobiologically inspired long-term memory for large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.344872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5b59579f-e527-4887-ae78-191cec470181 · outbound

This paper cites Hipporag: Neurobiologically inspired long-term memory for large language models, 2025.

Harmonia: End-to-End RAG Serving Optimization Hipporag: Neurobiologically inspired long-term memory for large language models, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.325670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a4294cf2-6451-4ec3-9b4a-11270090e3ff · outbound

This paper cites Retrieval-Augmented Generation with Graphs (GraphRAG).

Harmonia: End-to-End RAG Serving Optimization Retrieval-Augmented Generation with Graphs (GraphRAG)

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.433410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6800c883-0114-4076-983b-008334cc0724 · outbound

This paper cites Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations.

Harmonia: End-to-End RAG Serving Optimization Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.439592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0a8b22-bb5b-47de-aa80-23ac4f533e69 · outbound

This paper cites MOSEL: Inference serving using dynamic modality selec- tion.

Harmonia: End-to-End RAG Serving Optimization MOSEL: Inference serving using dynamic modality selec- tion

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.307531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9a31c2f9-5537-451d-8b58-e0f51729b5b3 · outbound

This paper cites RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving.

Harmonia: End-to-End RAG Serving Optimization RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.457808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b79768f-e2fc-4e50-b215-73d0c07ce3dd · outbound

This paper cites Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models.

Harmonia: End-to-End RAG Serving Optimization Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.464445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ebfefd1-a91b-49bb-8216-e347fa90ff5b · outbound

This paper cites PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design.

Harmonia: End-to-End RAG Serving Optimization PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.470123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400ad052-cf0b-4a6b-bbdb-03a76ba5a067 · outbound

This paper cites Active retrieval augmented generation.

Harmonia: End-to-End RAG Serving Optimization Active retrieval augmented generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.475868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8e8a23-abf1-4809-8dda-486c8ceb0011 · outbound

This paper cites FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research.

Harmonia: End-to-End RAG Serving Optimization FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.482339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af1aba66-2013-49c6-9be2-f5b4181967c7 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Harmonia: End-to-End RAG Serving Optimization Efficient memory management for large language model serving with pagedattention

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.262401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08c53ec4-5543-4b77-9b66-fbde3b247873 · outbound

This paper cites https: //www.langchain.com/langgraph.

Harmonia: End-to-End RAG Serving Optimization https: //www.langchain.com/langgraph

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.246570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 756e2512-3bf2-4e1e-9d52-a6d6be35a141 · outbound

This paper cites Pre-training via paraphrasing.

Harmonia: End-to-End RAG Serving Optimization Pre-training via paraphrasing

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.230614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 660f2646-74e7-4f84-a952-7e0e4e360aa8 · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.

Harmonia: End-to-End RAG Serving Optimization Retrieval-augmented generation for knowledge- intensive nlp tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.503739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3e35de-7ded-40a9-8eef-b33eb6f88eb9 · outbound

This paper cites DMQR-RAG: Diverse Multi-Query Rewriting for RAG.

Harmonia: End-to-End RAG Serving Optimization DMQR-RAG: Diverse Multi-Query Rewriting for RAG

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.510602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b30856-9e07-4731-b0df-4c7c6676e938 · outbound

This paper cites Cft-rag: An entity tree based retrieval augmented generation algorithm with cuckoo filter.

Harmonia: End-to-End RAG Serving Optimization Cft-rag: An entity tree based retrieval augmented generation algorithm with cuckoo filter

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.516531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d78fbc1-f13e-4f76-9b56-b47f321e7b8b · outbound

This paper cites Lyra: A Benchmark for Turducken-Style Code Generation.

Harmonia: End-to-End RAG Serving Optimization Lyra: A Benchmark for Turducken-Style Code Generation

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-08-16T04:40:05.316490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ad6e1feb-494d-41a6-8e98-4302eca50474 · outbound

This paper cites SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model.

Harmonia: End-to-End RAG Serving Optimization SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.530104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e38208-24c6-4f7f-9f16-d6c84ad8be77 · outbound

This paper cites TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval.

Harmonia: End-to-End RAG Serving Optimization TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.535865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d350887-30a9-4832-814c-7c249bc2773b · outbound

This paper cites HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation.

Harmonia: End-to-End RAG Serving Optimization HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.541391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79888576-0285-4cb8-ba30-8a1750943adb · outbound

This paper cites https://github.com/ggml-org/llama.cpp.

Harmonia: End-to-End RAG Serving Optimization https://github.com/ggml-org/llama.cpp

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.204412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a08988d7-08fb-42d4-94aa-c44923cd2916 · outbound

This paper cites Query rewriting in retrieval-augmented large language models.

Harmonia: End-to-End RAG Serving Optimization Query rewriting in retrieval-augmented large language models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.555085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07154bd2-33a6-4511-b758-219cc2c05447 · outbound

This paper cites Luminirag: Vision-enhanced graph rag for complex multi-modal document understanding.

Harmonia: End-to-End RAG Serving Optimization Luminirag: Vision-enhanced graph rag for complex multi-modal document understanding

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.173894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bee64b80-c58e-449c-91a5-cdef69b47ff3 · outbound

This paper cites Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow.

Harmonia: End-to-End RAG Serving Optimization Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.566083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44bd4015-5e3a-4056-9413-f562359e5fc3 · outbound

This paper cites Mllib: Machine learning in apache spark.

Harmonia: End-to-End RAG Serving Optimization Mllib: Machine learning in apache spark

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.156742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6173bb5b-dead-4e18-ac3f-77a16766373f · outbound

This paper cites Sosecure: Safer code generation with rag and stackoverflow discussions.

Harmonia: End-to-End RAG Serving Optimization Sosecure: Safer code generation with rag and stackoverflow discussions

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.580156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5c2e7f5-9762-40d5-a8fa-4a69151d6750 · outbound

This paper cites {Heterogeneity-Aware} cluster scheduling policies for deep learning workloads.

Harmonia: End-to-End RAG Serving Optimization {Heterogeneity-Aware} cluster scheduling policies for deep learning workloads

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.585672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4060c2d9-12ea-42ad-9270-882ec6f50c45 · outbound

This paper cites W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering.

Harmonia: End-to-End RAG Serving Optimization W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.590425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f32610f-6597-48bc-a4ae-50505ff32eea · outbound

This paper cites Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving.

Harmonia: End-to-End RAG Serving Optimization Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.595609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd35576-d9d3-4e2a-b9e4-a4b2b763d2d8 · outbound

This paper cites Fastertransformer.

Harmonia: End-to-End RAG Serving Optimization Fastertransformer

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.122359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e1a2a7a0-8589-4c17-95b9-0d7a3176f93c · outbound

This paper cites https://github.com/digithree/ollama-rag.

Harmonia: End-to-End RAG Serving Optimization https://github.com/digithree/ollama-rag

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.102901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5be3f135-7410-4c98-9307-5549ffe3273d · outbound

This paper cites Automatic differentiation in pytorch.

Harmonia: End-to-End RAG Serving Optimization Automatic differentiation in pytorch

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.613290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e29e67f-5e8e-49fe-a5e1-7f2324d7e14b · outbound

This paper cites https://peps.

Harmonia: End-to-End RAG Serving Optimization https://peps

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.062588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 121fba99-3797-47db-8605-b6396e9c6612 · outbound

This paper cites LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain.

Harmonia: End-to-End RAG Serving Optimization LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.624736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ef819c-5c5c-42dd-94a0-96ba64d635f6 · outbound

This paper cites MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation.

Harmonia: End-to-End RAG Serving Optimization MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.630238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12894818-0487-4539-9a45-3ecee558c121 · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

Harmonia: End-to-End RAG Serving Optimization SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.635383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f08244-6cb2-4cc1-adad-ec42e846a3b7 · outbound

This paper cites Ragserve: Fast quality- aware rag systems with configuration adaptation.

Harmonia: End-to-End RAG Serving Optimization Ragserve: Fast quality- aware rag systems with configuration adaptation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.639855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5dcc81c-04b3-4bc1-9c90-ef2bb393d265 · outbound

This paper cites {INFaaS}: Automated model-less inference serving.

Harmonia: End-to-End RAG Serving Optimization {INFaaS}: Automated model-less inference serving

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.040475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 26876c39-44b5-4837-b6be-d09ef05a4c35 · outbound

This paper cites Scaling retrieval-based language models with a trillion-token datastore.

Harmonia: End-to-End RAG Serving Optimization Scaling retrieval-based language models with a trillion-token datastore

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:06.018728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bf8dbfce-5e62-4106-9579-b16deb876ec1 · outbound

This paper cites Nexus: A gpu cluster engine for accelerating dnn-based video analysis.

Harmonia: End-to-End RAG Serving Optimization Nexus: A gpu cluster engine for accelerating dnn-based video analysis

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.997795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7913936e-f91e-45a8-89b6-ae3c5226b420 · outbound

This paper cites Flexgen: high-throughput generative inference of large language mod- els with a single gpu.

Harmonia: End-to-End RAG Serving Optimization Flexgen: high-throughput generative inference of large language mod- els with a single gpu

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.979042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 586e5631-77df-49f0-819c-fd81d9e1ab15 · outbound

This paper cites Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems.

Harmonia: End-to-End RAG Serving Optimization Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.664531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c00f0ed5-62b8-462c-aff0-d3ca2e617aee · outbound

This paper cites ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems.

Harmonia: End-to-End RAG Serving Optimization ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.670737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95aa3256-f70e-4aea-a9b0-08f7e75a74fa · outbound

This paper cites The hippocampal memory indexing theory.

Harmonia: End-to-End RAG Serving Optimization The hippocampal memory indexing theory

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.958418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7ccea840-e13a-4ad4-ab27-4a4c6cf51729 · outbound

This paper cites Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions.

Harmonia: End-to-End RAG Serving Optimization Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.682085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3b41878-2820-46fa-803b-f8fbc093b328 · outbound

This paper cites Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions, 2023.

Harmonia: End-to-End RAG Serving Optimization Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions, 2023

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.687906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b6c6681-c458-4aef-9c09-b5bdbbab70b2 · outbound

This paper cites Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions.

Harmonia: End-to-End RAG Serving Optimization Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.922090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0a3f5792-bb55-4e1a-97ac-7a440cf04e6e · outbound

This paper cites InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining.

Harmonia: End-to-End RAG Serving Optimization InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.697480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4085768a-b00e-4f53-bc4c-7d8cc79a94b5 · outbound

This paper cites RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation.

Harmonia: End-to-End RAG Serving Optimization RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.703888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef123b6-cd79-4b57-9140-01a1cfeb7e20 · outbound

This paper cites Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting.

Harmonia: End-to-End RAG Serving Optimization Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.709408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b24e9d14-8ae8-4b3d-9a6d-dcb1e882d17e · outbound

This paper cites Chain-of-thought prompt- ing elicits reasoning in large language models.

Harmonia: End-to-End RAG Serving Optimization Chain-of-thought prompt- ing elicits reasoning in large language models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.714961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b493bd-43a4-4b37-a10d-b931e883f563 · outbound

This paper cites https://www.octomind.dev/blog/why-we-no-longer-use-langchain- for-building-our-ai-agents.

Harmonia: End-to-End RAG Serving Optimization https://www.octomind.dev/blog/why-we-no-longer-use-langchain- for-building-our-ai-agents

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.887797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4f593372-3444-45af-9ecf-0cd66f95130f · outbound

This paper cites Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation.

Harmonia: End-to-End RAG Serving Optimization Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.725922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7069e26-3cc5-4821-9209-fac8701df47c · outbound

This paper cites Irina: Accelerating dnn inference with efficient online scheduling.

Harmonia: End-to-End RAG Serving Optimization Irina: Accelerating dnn inference with efficient online scheduling

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.870745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f07dd24-355b-41cc-a205-72e32949675d · outbound

This paper cites Tkg-rag: A retrieval-augmented generation framework with text-chunk knowl- edge graph.

Harmonia: End-to-End RAG Serving Optimization Tkg-rag: A retrieval-augmented generation framework with text-chunk knowl- edge graph

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.838382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 86a5eb53-5083-456e-8345-e9e0d5ab926c · outbound

This paper cites Corrective retrieval augmented generation.

Harmonia: End-to-End RAG Serving Optimization Corrective retrieval augmented generation

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.819297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3d4d4ae7-0004-48d6-bd42-dc9f9453d793 · outbound

This paper cites Wikiqa: A challenge dataset for open-domain question answering.

Harmonia: End-to-End RAG Serving Optimization Wikiqa: A challenge dataset for open-domain question answering

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.798597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9d037070-347f-4c0e-8371-c9ed2de37c99 · outbound

This paper cites Orca: A distributed serving system for {Transformer-Based} generative models.

Harmonia: End-to-End RAG Serving Optimization Orca: A distributed serving system for {Transformer-Based} generative models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.758024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b691b4-b7fe-433a-a9ec-78322086479e · outbound

This paper cites Spark: Cluster computing with working sets.

Harmonia: End-to-End RAG Serving Optimization Spark: Cluster computing with working sets

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.767757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation be04f45a-85c2-466b-9016-0530ae977b42 · outbound

This paper cites SHEP- HERD: Serving DNNs in the wild.

Harmonia: End-to-End RAG Serving Optimization SHEP- HERD: Serving DNNs in the wild

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.769148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95211b6e-e774-48d8-950a-45cf07a5c0b0 · outbound

This paper cites Raft: Adapting language model to domain specific rag.

Harmonia: End-to-End RAG Serving Optimization Raft: Adapting language model to domain specific rag

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:05.738737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3eb1b92f-2684-4ab2-b336-74e35daf7844 · outbound

This paper cites Accelerating Retrieval-Augmented Language Model Serving with Speculation.

Harmonia: End-to-End RAG Serving Optimization Accelerating Retrieval-Augmented Language Model Serving with Speculation

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.778794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00736cd-e37e-4693-ab4d-b4ac076adb03 · outbound

This paper cites P Xing, Joseph E.

Harmonia: End-to-End RAG Serving Optimization P Xing, Joseph E

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.783073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb470d0-071a-476c-8b8f-3ca5ca5439a8 · outbound

This paper cites Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning.

Harmonia: End-to-End RAG Serving Optimization Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.787699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f05b62-1e93-404a-9887-ca55bb14af4c · outbound

This paper cites an unresolved cited work.

Harmonia: End-to-End RAG Serving Optimization Unresolved cited work

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.736089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd7fb93-433b-4543-aa06-51771e9919f2 · outbound

This paper cites an unresolved cited work.

Harmonia: End-to-End RAG Serving Optimization Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:04.452536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers