2026-07-23

Internal Generation Record

Internal generation metadata: 305 candidate papers.

Published 2026-07-23 Target source 2026-07-21 Actual source 2026-07-21 Candidates 305 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 2026-07-22T22:14:16.213871+00:00. Generated at 2026-07-22T22:15:36.301721+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1make agents use tools and reusable skills more reliablyCode Intelligence2607.19338
2make RAG retrieval and knowledge-base QA more reliableTraining and Post-training2607.19171
3make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.18826
4improve model reasoning, planning, and verificationReasoning and Planning2607.18820
7make RAG retrieval and knowledge-base QA more reliableData Engineering2607.18875
9make RAG retrieval and knowledge-base QA more reliableSafety and Alignment2607.19292
5improve model reasoning, planning, and verificationReasoning and Planning2607.19194
6make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.19069
8make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.18786
10improve model reasoning, planning, and verificationReasoning and Planning2607.19288
11identify and reduce safety, jailbreak, and alignment risksSafety and Alignment2607.19243
12make agents use tools and reusable skills more reliablyTraining and Post-training2607.19191
13strengthen multimodal understanding of charts, documents, and visual evidenceVision and Image Generation2607.19064
14make agents use tools and reusable skills more reliablyData Engineering2607.19036
15strengthen multimodal understanding of charts, documents, and visual evidenceTraining and Post-training2607.18966
16improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.18912
17make agents use tools and reusable skills more reliablyData Engineering2607.18642
18make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2607.18602
19improve model reasoning, planning, and verificationMultimodal Models2607.19341
20make agents use tools and reusable skills more reliablyTraining and Post-training2607.19339
21make agents use tools and reusable skills more reliablyAgents and Tool Use2607.19336
22make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.19322
23make agents use tools and reusable skills more reliablyAgents and Tool Use2607.19321
24make agents use tools and reusable skills more reliablyInterpretability2607.19317
25improve model reasoning, planning, and verificationTraining and Post-training2607.19219
26make agents use tools and reusable skills more reliablyAgents and Tool Use2607.19190