Paper Citation Record · LEDGER

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

As of 5 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 3 inbound Pith citation observations for arXiv:2605.20315.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2605.20315 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T07:49:07.128814Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T07:06:53.318182Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-01T08:55:35.141369Z

Reference resolution

46 of 46 outbound references displayed

verified exact20
verified fuzzy24
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2a385ae5-409d-4994-a3d1-b1d0e5a84019 · outbound

This paper cites Artificial Analysis Long Context Reasoning Benchmark (LCR).

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Artificial Analysis Long Context Reasoning Benchmark (LCR)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.378024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bfd33b8f-ffec-4025-a15d-5fc5cd592954 · outbound

This paper cites LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.972396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d60d51c5-5ca8-4497-8691-803ab1ee0d02 · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.969634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8d9f0956-f6e6-4d79-bdd7-042c0ceaf012 · outbound

This paper cites Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.966881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c328ebc-0313-47e2-8c9c-a44f3d222cbd · outbound

This paper cites LLM.int8(): 8-bit matrix multiplication for transformers at scale.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs LLM.int8(): 8-bit matrix multiplication for transformers at scale

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.375486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 83876ccb-db30-41d5-8d14-038885cbb3dc · outbound

This paper cites Castro, Denis Kuznedelev, Andrei Panferov, Eldar Kurtic, Shubhra Pandit, Alexandre Noll Marques, Mark Kurtz, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Castro, Denis Kuznedelev, Andrei Panferov, Eldar Kurtic, Shubhra Pandit, Alexandre Noll Marques, Mark Kurtz, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.960736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5e6cc91b-ea7b-49d7-8ecd-c3bf82c89e4b · outbound

This paper cites Flashprefill: Instantaneous pattern discovery and thresholding for ultra-fast long-context prefilling.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Flashprefill: Instantaneous pattern discovery and thresholding for ultra-fast long-context prefilling

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.964034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f9fff8a0-bbce-40e1-b314-09dfad0454a7 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.954601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0a4e6f92-18fa-4e0f-bd71-822871563cd5 · outbound

This paper cites Gemma 4 model card.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Gemma 4 model card

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.369854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a7a730a8-ebf4-45e5-a14d-ea7649504a96 · outbound

This paper cites Minillm: Knowledge distillation of large language models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Minillm: Knowledge distillation of large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.372980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ee3db034-e5b2-4b0a-b032-591650e2d55a · outbound

This paper cites Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.332349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8004bb3a-0bed-422c-a1d0-3bd81e3c2bda · outbound

This paper cites Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.326906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8cb856c8-3ed2-4fc2-ac3c-6fe52c7753b2 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.945471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation abc28438-7dda-45df-b37f-5c2852826b12 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Gonzalez, Hao Zhang, and Ion Stoica

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.353536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 90fb5a9d-bbc2-4524-9a97-b6bfe4c67954 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Gonzalez, Hao Zhang, and Ion Stoica

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.356126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 158e9f64-0ce8-4f9e-8897-f3016a719d5b · outbound

This paper cites Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.951742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 966e5100-4c5b-4625-8d49-4e5b9fba6d3d · outbound

This paper cites Let’s verify step by step.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Let’s verify step by step

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.348042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 92b365b2-bff3-4f2f-ab30-d9ec586a32e3 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of machine learning and systems, 6:87–100.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of machine learning and systems, 6:87–100

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.350994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 56797825-8cc6-46a0-8dcd-f8dca6ba2c0c · outbound

This paper cites MixReasoning: Switching Modes to Think.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs MixReasoning: Switching Modes to Think

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-09T03:07:04.833097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 758707e8-05c7-4f5a-8b56-31daaf3cf52c · outbound

This paper cites Large Language Model Agent: A Survey on Methodology, Applications and Challenges.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.938591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 640f6f26-8c8d-4ce5-b575-2edd0f7c2c9f · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.367035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6415345b-ed10-4db1-9c3f-9387d04bcf93 · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs WebGPT: Browser-assisted question-answering with human feedback

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.931375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0b4853b3-0cfe-415d-9688-3c6b64e32a4a · outbound

This paper cites Introducing nvfp4 for efficient and accurate low- precision inference.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Introducing nvfp4 for efficient and accurate low- precision inference

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.341227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 58ddcb9f-a327-44fe-900d-144b6f22b243 · outbound

This paper cites Enhancing distributed inference performance with the nvidia inference transfer library.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Enhancing distributed inference performance with the nvidia inference transfer library

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.313218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a9885126-92b7-4362-bfbf-91e10aa528d8 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs MemGPT: Towards LLMs as Operating Systems

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T07:49:49.957577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 64f81343-78c1-42a8-8efd-ee22672adb86 · outbound

This paper cites Splitwise: Efficient generative LLM inference using phase splitting.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Splitwise: Efficient generative LLM inference using phase splitting

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.924669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03ff802a-6c80-47b0-b22c-0eafdd6b0eee · outbound

This paper cites Splitwise: Efficient generative llm inference using phase splitting.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Splitwise: Efficient generative llm inference using phase splitting

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.363770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0413313e-6ec5-4d57-89c4-a587c93ba989 · outbound

This paper cites The berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs The berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.335327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation af2343a7-ab13-46d5-8779-0b74ef1a22a4 · outbound

This paper cites Yarn: Efficient context window extension of large language models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Yarn: Efficient context window extension of large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.358780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2d11e57d-a088-41c6-9ef7-db38a1ebaa7d · outbound

This paper cites Swiftkv: Fast prefill- optimized inference with knowledge-preserving model transformation.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Swiftkv: Fast prefill- optimized inference with knowledge-preserving model transformation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.360965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f816f20-a4cf-4c42-a24a-c331a75ff4b1 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Qwen3.5: Towards native multimodal agents, February 2026

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.344987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8e1723f9-b021-43fb-8365-6503ae1224c6 · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.948681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c33454c0-104a-41b1-84aa-e3a8e5d1aa77 · outbound

This paper cites Efficient llm serving for agentic workflows: A data systems perspective.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Efficient llm serving for agentic workflows: A data systems perspective

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.942271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 214e712c-589e-4792-a522-7a3d145eb1a2 · outbound

This paper cites Long- memeval: Benchmarking chat assistants on long-term interactive memory.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Long- memeval: Benchmarking chat assistants on long-term interactive memory

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.338241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dea70fbf-ce22-4e69-9d02-f5783188a110 · outbound

This paper cites Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.917837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 93a4fce7-f10d-403b-ae33-47e4d9f178d4 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.316161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8e16447e-4d6f-47e2-81ac-3273a059a3e1 · outbound

This paper cites A-MEM: Agentic Memory for LLM Agents.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs A-MEM: Agentic Memory for LLM Agents

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.920887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5b15b1b7-44ac-45a5-9a97-c39f280756c2 · outbound

This paper cites Qwen3 Technical Report.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Qwen3 Technical Report

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.928093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0c304cd2-c41b-49a0-aa34-45a9e3b0478d · outbound

This paper cites Swe-agent: Agent-computer interfaces enable automated software engineering.Advances in Neural Information Processing Systems, 37:50528–50652.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Swe-agent: Agent-computer interfaces enable automated software engineering.Advances in Neural Information Processing Systems, 37:50528–50652

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.324073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 082ef578-7e54-4091-a4f7-222a2731af2d · outbound

This paper cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Reference 42

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T07:49:49.905664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 18f6fe46-d908-4334-9e9f-5d0516f1bd76 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs ReAct: Synergizing Reasoning and Acting in Language Models

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.908832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 816b3edc-6414-470e-91e7-529ab802c486 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs React: Synergizing reasoning and acting in language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.318808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0c5816a9-3477-49f3-b916-015fa4e878ec · outbound

This paper cites Qspec: Speculative decoding with complementary quantization schemes.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Qspec: Speculative decoding with complementary quantization schemes

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.321487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d27ba4df-1089-46e6-9ff2-471ec59aa2f9 · outbound

This paper cites Atom: Low-bit Quantization for Efficient and Accurate LLM Serving.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:49.914962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c85e2897-eba7-4a5e-903e-a2a0ff37827c · outbound

This paper cites Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:49:50.329713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 96d6637d-aae8-4ddc-a106-0be1a467de59 · outbound

This paper cites A Survey on Efficient Inference for Large Language Models.

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs A Survey on Efficient Inference for Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:49:49.911867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation 25b1ed1e-ee39-4a35-97c2-0c3c676a14e3 · inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:04:45.308390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7ab5af06-553c-44c1-9326-0796ec6c9ade · inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-01T08:55:35.142489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation efe7403d-7d97-4a79-9285-2f95ab49a841 · inbound

HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators cites this paper.

HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:14:57.498059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.