2026-06-27

Internal Generation Record

Internal generation metadata: 386 candidate papers.

Published 2026-06-27 Target source 2026-06-25 Actual source 2026-06-25 Candidates 386 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 2026-06-26T22:21:39.824362+00:00. Generated at 2026-06-26T22:22:54.584961+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.26535
2make agents use tools and reusable skills more reliablyAgents and Tool Use2606.26590
3make agents use tools and reusable skills more reliablyRetrieval and RAG2606.26476
4make RAG retrieval and knowledge-base QA more reliableCode Intelligence2606.27287
11improve model reasoning, planning, and verificationReasoning and Planning2606.26686
13improve model reasoning, planning, and verificationTraining and Post-training2606.26530
5improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.27128
6strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2606.26984
7make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.26973
8make agents use tools and reusable skills more reliablyAgents and Tool Use2606.26859
9make agents use tools and reusable skills more reliablyAgents and Tool Use2606.26857
10improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.26794
12strengthen multimodal understanding of charts, documents, and visual evidenceBenchmarks and Evaluation2606.26566
14strengthen multimodal understanding of charts, documents, and visual evidenceVideo Generation2606.27317
15make agents use tools and reusable skills more reliablyAgents and Tool Use2606.27180
16test temporal consistency and motion realism in video generationSystems and Deployment2606.26861
17make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2606.26836
18make agents use tools and reusable skills more reliablyAgents and Tool Use2606.26790
19improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2606.26716
20make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.26712
21make RAG retrieval and knowledge-base QA more reliableCode Intelligence2606.27361
22make agents use tools and reusable skills more reliablyAgents and Tool Use2606.27330
23make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.27307
24make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.27275
25make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.27223
26improve model reasoning, planning, and verificationTraining and Post-training2606.27210