2026-07-26

Internal Generation Record

Internal generation metadata: 321 candidate papers.

Published 2026-07-26 Target source 2026-07-24 Actual source 2026-07-23 Candidates 321 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 2026-07-25T23:26:27.605704+00:00. Generated at 2026-07-25T23:27:49.077074+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
27improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.21063
28improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.21061
29improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.21057
30make RAG retrieval and knowledge-base QA more reliableVideo Generation2607.21027
31make agents use tools and reusable skills more reliablyAgents and Tool Use2607.21019
33improve model reasoning, planning, and verificationTraining and Post-training2607.20988
32make agents use tools and reusable skills more reliablyAgents and Tool Use2607.20999
34make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.20984
35make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.20957
36make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.20946
37improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.20925
38make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.20890
39make agents use tools and reusable skills more reliablyAgents and Tool Use2607.20872
40make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.20864
41make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.20862
42improve model reasoning, planning, and verificationRetrieval and RAG2607.20833
43make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.20814
44improve model reasoning, planning, and verificationReasoning and Planning2607.21550
45strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2607.21546
46make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.21438
47improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.21416
48improve model reasoning, planning, and verificationTraining and Post-training2607.21409
49improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.21370
50improve code generation, execution feedback, and automated repairTraining and Post-training2607.21356
51make RAG retrieval and knowledge-base QA more reliableMultimodal Models2607.21343
52improve model reasoning, planning, and verificationReasoning and Planning2607.21271