Pith. sign in

Paper Citation Record · LEDGER

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models

As of 14 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2608.06699.

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

pith.paper-citation-record.v1
2608.06699 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T22:17:20.650451Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

25 of 25 outbound references displayed

  • verified exact1
  • verified fuzzy3
  • unresolved20
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2e9fdf0d-dfad-4ff0-8297-1a0df984f59c · outbound

This paper cites Qwen3-VL Technical Report.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Qwen3-VL Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.522760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.522760Z digest=sha256:4e6e644aae67df51b9ae0adcd1c43a359f69815a7bf253cd5207b1f2cc5d61b0

Observation 0347e318-6720-4973-a3a4-c2e806d71ac7 · outbound

This paper cites boost" and target_span_role=.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models boost" and target_span_role=

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T22:17:21.235389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-10T22:17:20.650451Z digest=sha256:0b8027b00368ab6310a9fb9163f91f2864d16d1fbd7bc74a99fd3a3b610f3c5b

Observation 49ff3174-25a5-44a4-8d82-b8251aa504c7 · outbound

This paper cites WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.549845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.549845Z digest=sha256:b479c9650a7daaa38f0928d8cc868dd358e767e78c6fc56aadbe224d25e509a9

Observation c71f695d-fbda-4ab1-9fbb-434de0224940 · outbound

This paper cites Editing Models with Task Arithmetic.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Editing Models with Task Arithmetic

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.555161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.555161Z digest=sha256:7ffc79c90b2cfe1e75440d501f4187281d1206fb2712080f3d12942012b3c8d4

Observation e72d4eb7-94de-491f-9e30-356589a07f8d · outbound

This paper cites MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.560314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.560314Z digest=sha256:f9537e6d18451b35befbc32bd903a50bda702d528cb5542c00ca45275dd624ff

Observation 07d5ed07-85e5-447f-934a-df0c03bc7d95 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.565937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.565937Z digest=sha256:812e1452a6de4c7c2f8cbbbd03beddb08495ed6ef5560f083ffd5754f02647b4

Observation 7120a2ea-9ad7-44f4-9447-6d7938c778b4 · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.575730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.575730Z digest=sha256:cd545b38b308693b14280d8d921d7c8cf851d99044a4baa123f722702c262492

Observation d965c5f7-665d-4dd5-8c30-cb7acd8725a4 · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.581037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.581037Z digest=sha256:ddb0169853a7bf3369d6e7c49a2365c0df7fcb67c9cc3ae9495c3b20e1d82f24

Observation 996da348-9c30-4f61-9ec1-399c49e9819f · outbound

This paper cites PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.586165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.586165Z digest=sha256:e4a954e889ff8a381bb71f2c36b1f4de2e241da0ec88498fe864cb6f89db2e0f

Observation 02595c2c-f568-4c4a-98a6-ee81f61110d4 · outbound

This paper cites Model merging with SVD to tie the Knots.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Model merging with SVD to tie the Knots

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.591158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.591158Z digest=sha256:5983be19711614bcde8bbb4ac3b9a64cdbc1f617a7c69f9ace0e60df220ef8fd

Observation c24b86ed-329d-402c-bad3-7166f766b345 · outbound

This paper cites An Empirical Study of Multimodal Model Merging.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models An Empirical Study of Multimodal Model Merging

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.596112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.596112Z digest=sha256:831b081cfd31dc48eb7a3bacdc6971abf9c226389f51fe0870e00629343be5d2

Observation bdc3c68a-2aa8-4d37-a8b0-be7c79996098 · outbound

This paper cites Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.601571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.601571Z digest=sha256:118da832fea428cf1f72291f92a0fda1125673278a95986d7ef91db85efe22c8

Observation d2272cea-c46a-40cd-ac6e-c3149097f2b9 · outbound

This paper cites Wortsman, M.; Ilharco, G.; Gadre, S.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Wortsman, M.; Ilharco, G.; Gadre, S

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.607703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.607703Z digest=sha256:6ae18d1fc18f7efaebcfcc29282bc58956b947518ce25abba180f73e967b09e6

Observation 97be0b3f-9e47-4d58-b683-133ab4355bcb · outbound

This paper cites MMSearch-R1: Incentivizing LMMs to Search.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models MMSearch-R1: Incentivizing LMMs to Search

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.613684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.613684Z digest=sha256:97744c2e87dceb39c9a86fa25efc09fb8d794bb2d687ba8c66aba48ee0cd1537

Observation dada7984-74ec-4417-be64-008b1daadaac · outbound

This paper cites V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.618767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.618767Z digest=sha256:ea77bbf29eb87c6e048cdea121168efb17d492199e10f46bde7a12baa5e52a71

Observation b5f765bf-6197-4d5d-b6c6-e45db8333871 · outbound

This paper cites OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.624057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.624057Z digest=sha256:8c4b67d8eff379ca3323855043ad92db3a3c23d240e4abcdf67a731b647ec110

Observation 60cbf84e-d2df-4f65-9e7f-4571cb1549e9 · outbound

This paper cites Yao, H.; Zhang, R.; Huang, J.; Zhang, J.; Wang, Y.; Fang, B.;Zhu,R.;Jing,Y.;Liu,S.;Li,G.;etal.2025.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Yao, H.; Zhang, R.; Huang, J.; Zhang, J.; Wang, Y.; Fang, B.;Zhu,R.;Jing,Y.;Liu,S.;Li,G.;etal.2025

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.629213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.629213Z digest=sha256:eb910dc000abdbbc5845d5a79f37c5a9f21e4bfe1596a364275942a47b82a5e6

Observation e82bea39-2ef6-4c68-a11c-43b65fdfbc0e · outbound

This paper cites Mobile-Agent-v3: Fundamental Agents for GUI Automation.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Mobile-Agent-v3: Fundamental Agents for GUI Automation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.634729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.634729Z digest=sha256:9b12d00e62f78bfa2a92745f63a9524e7a0a9515b5f433e87b305b45835ccb54

Observation 4a5e0248-1d64-47a1-be09-a89ae4d0038a · outbound

This paper cites InNeurIPS 2025 Fourth Workshop on Deep Learning for Code.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models InNeurIPS 2025 Fourth Workshop on Deep Learning for Code

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T22:17:21.252467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-10T22:17:20.639674Z digest=sha256:df8a113687278dec1fb643dd7783a60cf65c0361e3cc727b656b62c611925e9f

Observation 9d191a33-8eaf-4d99-a593-7084d24e0a83 · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 24

Resolution
malformed identifier
no resolver link, observed 2026-08-10T22:17:20.644602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.644602Z digest=sha256:d2f017aff44462ef0bd76c23ed0a88118d6b5363fa1e05d50bf02d54574d9306

Observation 939c5c5d-0bef-4e7d-8f93-7135242bcb5d · outbound

This paper cites Fusing finetuned models for better pretraining.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Fusing finetuned models for better pretraining

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.533940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.533940Z digest=sha256:78c701ad7225b9fa6f2895a15d655944b163bca9246e34dd707f66d4adea2a95

Observation 9d7ab4e6-6a83-48b4-ad34-cc6ae47372d6 · outbound

This paper cites an unresolved cited work.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Unresolved cited work

Reference 2023

Resolution
unresolved
raw_fallback, observed 2026-08-10T22:17:21.268980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-10T22:17:20.570869Z digest=sha256:3e0449df0941ffed74afdaae43f9cc707fe455ce59fb9cfe46c5048c89abd747

Observation 7b2cf31a-55fb-4e73-b388-530d895952fa · outbound

This paper cites Model Composition for Multimodal Large Language Models.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Model Composition for Multimodal Large Language Models

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-10T22:17:20.528557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:17:20.528557Z digest=sha256:e025d8cb78f8fe5b879269086ef85ee66d3d0cf8c9512795ce8debf1d23a61ab

Observation a62d651f-160b-4023-b523-a2f79a55c6d7 · outbound

This paper cites In Proceedings of the Computer Vision and Pattern Recogni- tion Conference, 18695–18705.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models In Proceedings of the Computer Vision and Pattern Recogni- tion Conference, 18695–18705

Reference 2025

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T22:17:21.284530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-10T22:17:20.544787Z digest=sha256:bc75308840a8d57644c3777ce4b171ca212f238caa2d0acdd9bf3fd7666b56e6

Observation 74aaefc1-7526-4e89-9f29-06959450623e · outbound

This paper cites Gargiulo, A.

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models Gargiulo, A

Reference 2026

Resolution
verified exact
raw_fallback, observed 2026-08-10T22:17:21.171648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-10T22:17:20.539668Z digest=sha256:bc5a36069d0815bc983db3f36d49a21d51b952dec0d11920752713893417119b

Pith citing papers

No inbound Pith citation observations are available.