2026-07-20

Internal Generation Record

Internal generation metadata: 326 candidate papers.

Published 2026-07-20 Target source 2026-07-18 Actual source 2026-07-16 Candidates 326 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 2026-07-19T22:07:11.714043+00:00. Generated at 2026-07-19T22:08:30.753153+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
53make agents use tools and reusable skills more reliablyAgents and Tool Use2607.15218
54improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.15202
55improve code generation, execution feedback, and automated repairData Engineering2607.15166
56improve model reasoning, planning, and verificationTraining and Post-training2607.15161
58improve model reasoning, planning, and verificationRobotics and Embodied AI2607.15065
59improve image generation, visual understanding, and controllable renderingVision and Image Generation2607.14990
57make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.15114
60improve image generation, visual understanding, and controllable renderingBenchmarks and Evaluation2607.14984
61make agents use tools and reusable skills more reliablySpeech and Audio2607.14846
62improve code generation, execution feedback, and automated repairVideo Generation2607.14836
63make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.14817
64improve code generation, execution feedback, and automated repairInterpretability2607.14791
65improve code generation, execution feedback, and automated repairVision and Image Generation2607.14765
66improve code generation, execution feedback, and automated repairVideo Generation2607.14726
67improve model reasoning, planning, and verificationInterpretability2607.14720
68make RAG retrieval and knowledge-base QA more reliableVideo Generation2607.14708
69make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.14707
70make RAG retrieval and knowledge-base QA more reliableCode Intelligence2607.14655
71make agents use tools and reusable skills more reliablyTraining and Post-training2607.14643
72make RAG retrieval and knowledge-base QA more reliableCode Intelligence2607.14622
73test temporal consistency and motion realism in video generationBenchmarks and Evaluation2607.14607
74improve model reasoning, planning, and verificationTraining and Post-training2607.14560
75make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.14509
76improve model reasoning, planning, and verificationVideo Generation2607.15278
77make agents use tools and reusable skills more reliablyRetrieval and RAG2607.15253
78make agents use tools and reusable skills more reliablyMultimodal Models2607.15246