2026-07-12

Internal Generation Record

Internal generation metadata: 291 candidate papers.

Published 2026-07-12 Target source 2026-07-10 Actual source 2026-07-09 Candidates 291 Featured 6 Tracked 20 Source date fallback

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 2026-07-11T22:02:31.917746+00:00. Generated at 2026-07-11T22:03:45.996790+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
27make agents use tools and reusable skills more reliablyAgents and Tool Use2607.08691
28make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.08681
29make RAG retrieval and knowledge-base QA more reliableMultimodal Models2607.08605
30improve image generation, visual understanding, and controllable renderingBenchmarks and Evaluation2607.08515
36make agents use tools and reusable skills more reliablyData Engineering2607.08375
37improve image generation, visual understanding, and controllable renderingTraining and Post-training2607.08368
31improve model reasoning, planning, and verificationMultimodal Models2607.08503
32improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.08434
33make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.08423
34make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.08397
35make agents use tools and reusable skills more reliablyAgents and Tool Use2607.08395
38improve model reasoning, planning, and verificationMultimodal Models2607.08359
39improve code generation, execution feedback, and automated repairRetrieval and RAG2607.08332
40improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.08284
41make agents use tools and reusable skills more reliablyAgents and Tool Use2607.08282
42strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2607.08267
43improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.08257
44strengthen multimodal understanding of charts, documents, and visual evidenceTraining and Post-training2607.08194
45make agents use tools and reusable skills more reliablyTraining and Post-training2607.08182
46make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.08164
47make RAG retrieval and knowledge-base QA more reliableData Engineering2607.08122
48make agents use tools and reusable skills more reliablyAgents and Tool Use2607.08093
49make agents use tools and reusable skills more reliablyData Engineering2607.08080
50make agents use tools and reusable skills more reliablyTraining and Post-training2607.08072
51make agents use tools and reusable skills more reliablySafety and Alignment2607.08066
52improve model reasoning, planning, and verificationReasoning and Planning2607.08056