2026-07-05

Internal Generation Record

Internal generation metadata: 445 candidate papers.

Published 2026-07-05 Target source 2026-07-03 Actual source 2026-07-02 Candidates 445 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 2026-07-04T22:08:18.771002+00:00. Generated at 2026-07-04T22:09:55.858029+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
27make RAG retrieval and knowledge-base QA more reliableSafety and Alignment2607.01859
28improve code generation, execution feedback, and automated repairCode Intelligence2607.01785
29make agents use tools and reusable skills more reliablyAgents and Tool Use2607.01754
30improve model reasoning, planning, and verificationSafety and Alignment2607.02510
31improve model reasoning, planning, and verificationRetrieval and RAG2607.02509
34make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.02496
32make agents use tools and reusable skills more reliablyAgents and Tool Use2607.02507
33make agents use tools and reusable skills more reliablyAgents and Tool Use2607.02497
35make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.02469
36make agents use tools and reusable skills more reliablyReasoning and Planning2607.02376
37make agents use tools and reusable skills more reliablyAgents and Tool Use2607.02345
38improve model reasoning, planning, and verificationReasoning and Planning2607.02300
39improve image generation, visual understanding, and controllable renderingBenchmarks and Evaluation2607.02291
40make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.02284
41improve model reasoning, planning, and verificationRetrieval and RAG2607.02262
42make RAG retrieval and knowledge-base QA more reliableData Engineering2607.02254
43make agents use tools and reusable skills more reliablyAgents and Tool Use2607.02245
44make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.02220
45make agents use tools and reusable skills more reliablyAgents and Tool Use2607.02210
46make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.02201
47improve code generation, execution feedback, and automated repairTraining and Post-training2607.02194
48make agents use tools and reusable skills more reliablyRetrieval and RAG2607.02121
49make RAG retrieval and knowledge-base QA more reliableMultimodal Models2607.02097
50strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2607.02091
51make agents use tools and reusable skills more reliablyRetrieval and RAG2607.02083
52make agents use tools and reusable skills more reliablyRetrieval and RAG2607.02079