2026-06-11

Internal Generation Record

Internal generation metadata: 558 candidate papers.

Published 2026-06-11 Target source 2026-06-09 Actual source 2026-06-09 Candidates 558 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 2026-06-11T01:22:49.568665+00:00. Generated at 2026-06-11T01:24:12.311044+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1make agents use tools and reusable skills more reliablyCode Intelligence2606.11416
2make agents use tools and reusable skills more reliablyReasoning and Planning2606.11470
3improve model reasoning, planning, and verificationData Engineering2606.10602
4make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.11289
5make agents use tools and reusable skills more reliablyRetrieval and RAG2606.11150
7make agents use tools and reusable skills more reliablyTraining and Post-training2606.11507
6make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.11257
8make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2606.11435
9make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.11382
10improve code generation, execution feedback, and automated repairSafety and Alignment2606.11316
11strengthen multimodal understanding of charts, documents, and visual evidenceMultimodal Models2606.11190
12strengthen multimodal understanding of charts, documents, and visual evidenceMultimodal Models2606.11188
13make RAG retrieval and knowledge-base QA more reliableMultimodal Models2606.11106
14strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2606.10862
15improve model reasoning, planning, and verificationTraining and Post-training2606.10796
16make agents use tools and reusable skills more reliablyAgents and Tool Use2606.10747
17make agents use tools and reusable skills more reliablyAgents and Tool Use2606.10522
18improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.10403
19make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.10309
20make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.10287
21improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2606.11381
22identify and reduce safety, jailbreak, and alignment risksBenchmarks and Evaluation2606.11123
23improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2606.11098
24make agents use tools and reusable skills more reliablyAgents and Tool Use2606.10813
25strengthen multimodal understanding of charts, documents, and visual evidenceMultimodal Models2606.10640
26make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.10621