2026-07-25

Internal Generation Record

Internal generation metadata: 321 candidate papers.

Published 2026-07-25 Target source 2026-07-23 Actual source 2026-07-23 Candidates 321 Featured 6 Tracked 20

Generation Record

This page preserves selected papers, candidate scale, and source-date metadata for traceability. The page only changes presentation, not selected papers, ordering, or counts.

Internal generation record. Fetched at 2026-07-24T22:15:37.712478+00:00. Generated at 2026-07-24T22:16:58.592304+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21518
2make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.21471
3strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2607.21384
4improve code generation, execution feedback, and automated repairVision and Image Generation2607.21591
6improve model reasoning, planning, and verificationMultimodal Models2607.21401
11improve code generation, execution feedback, and automated repairCode Intelligence2607.21197
5make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21482
7make agents use tools and reusable skills more reliablyVision and Image Generation2607.21371
8make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.20911
9make RAG retrieval and knowledge-base QA more reliableMultimodal Models2607.20903
10improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.21281
12make RAG retrieval and knowledge-base QA more reliableSafety and Alignment2607.21151
13make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.21042
14make RAG retrieval and knowledge-base QA more reliableData Engineering2607.21526
15strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2607.21496
16make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21495
17make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21412
18make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.21332
19make agents use tools and reusable skills more reliablyTraining and Post-training2607.21326
20improve model reasoning, planning, and verificationTraining and Post-training2607.21291
21make RAG retrieval and knowledge-base QA more reliableVision and Image Generation2607.21243
22make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21217
23improve image generation, visual understanding, and controllable renderingBenchmarks and Evaluation2607.21137
24make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.21076
25improve model reasoning, planning, and verificationReasoning and Planning2607.21074
26improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.21069