2026-06-23

Internal Generation Record

Internal generation metadata: 419 candidate papers.

Published 2026-06-23 Target source 2026-06-21 Actual source 2026-06-18 Candidates 419 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 2026-06-23T00:48:16.693238+00:00. Generated at 2026-06-23T00:49:44.907486+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
79make RAG retrieval and knowledge-base QA more reliableCode Intelligence2606.20174
80make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.20173
81improve code generation, execution feedback, and automated repairData Engineering2606.20172
82make agents use tools and reusable skills more reliablyVideo Generation2606.20161
83strengthen multimodal understanding of charts, documents, and visual evidenceTraining and Post-training2606.20101
84improve image generation, visual understanding, and controllable renderingBenchmarks and Evaluation2606.20084
85improve model reasoning, planning, and verificationReasoning and Planning2606.20082
86make agents use tools and reusable skills more reliablyReasoning and Planning2606.20075
87improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.20068
88make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2606.20053
89test temporal consistency and motion realism in video generationSystems and Deployment2606.20031
90test temporal consistency and motion realism in video generationSystems and Deployment2606.19993
91make RAG retrieval and knowledge-base QA more reliableCode Intelligence2606.19964
92improve code generation, execution feedback, and automated repairMultimodal Models2606.19901
93make RAG retrieval and knowledge-base QA more reliableSystems and Deployment2606.19849
94make RAG retrieval and knowledge-base QA more reliableInterpretability2606.19831
95make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.19824
96improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2606.19819
97improve model reasoning, planning, and verificationReasoning and Planning2606.19808
98make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.19803
99improve code generation, execution feedback, and automated repairCode Intelligence2606.19799
100use benchmarks and evaluations to expose model weaknessesTraining and Post-training2606.19734
101make agents use tools and reusable skills more reliablyAgents and Tool Use2606.19727
102make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.19700
103improve code generation, execution feedback, and automated repairVision and Image Generation2606.20563
104improve model reasoning, planning, and verificationReasoning and Planning2606.20560