2026-07-16

Internal Generation Record

Internal generation metadata: 307 candidate papers.

Published 2026-07-16 Target source 2026-07-14 Actual source 2026-07-14 Candidates 307 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 2026-07-15T22:10:48.034010+00:00. Generated at 2026-07-15T22:12:11.174535+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.12835
2make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.12659
3improve model reasoning, planning, and verificationVideo Generation2607.12787
4make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.12704
6make agents use tools and reusable skills more reliablyAgents and Tool Use2607.13034
7improve model reasoning, planning, and verificationTraining and Post-training2607.12858
5make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.12227
8improve model reasoning, planning, and verificationVision and Image Generation2607.12602
9make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2607.12599
10improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.12370
11make agents use tools and reusable skills more reliablyAgents and Tool Use2607.13028
12make agents use tools and reusable skills more reliablyAgents and Tool Use2607.13027
13improve code generation, execution feedback, and automated repairTraining and Post-training2607.13010
14improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.12946
15make agents use tools and reusable skills more reliablyRetrieval and RAG2607.12911
16make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.12896
17improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.12881
18improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.12856
19make agents use tools and reusable skills more reliablyRetrieval and RAG2607.12818
20make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.12792
21make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.12790
22improve model reasoning, planning, and verificationMultimodal Models2607.12786
23make agents use tools and reusable skills more reliablyRetrieval and RAG2607.12784
24make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.12763
25make agents use tools and reusable skills more reliablyVideo Generation2607.12753
26make agents use tools and reusable skills more reliablyInterpretability2607.12739