2026-07-08

Internal Generation Record

Internal generation metadata: 369 candidate papers.

Published 2026-07-08 Target source 2026-07-06 Actual source 2026-07-06 Candidates 369 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 2026-07-07T22:20:32.207446+00:00. Generated at 2026-07-07T22:21:54.326111+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.05389
2improve code generation, execution feedback, and automated repairTraining and Post-training2607.05356
3make agents use tools and reusable skills more reliablyAgents and Tool Use2607.05055
4make agents use tools and reusable skills more reliablyVideo Generation2607.04812
5improve code generation, execution feedback, and automated repairVision and Image Generation2607.04691
8make RAG retrieval and knowledge-base QA more reliableMultimodal Models2607.04559
6improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.04607
7improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.04599
9make agents use tools and reusable skills more reliablyVideo Generation2607.05352
10improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2607.04825
11make RAG retrieval and knowledge-base QA more reliableRobotics and Embodied AI2607.05396
12test temporal consistency and motion realism in video generationBenchmarks and Evaluation2607.05365
13improve code generation, execution feedback, and automated repairTraining and Post-training2607.05364
14make agents use tools and reusable skills more reliablyAgents and Tool Use2607.05363
15improve model reasoning, planning, and verificationReasoning and Planning2607.05353
16improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.05311
17strengthen multimodal understanding of charts, documents, and visual evidenceMultimodal Models2607.05310
18improve code generation, execution feedback, and automated repairInterpretability2607.05306
19make agents use tools and reusable skills more reliablyAgents and Tool Use2607.05281
20improve model reasoning, planning, and verificationBenchmarks and Evaluation2607.05264
21improve code generation, execution feedback, and automated repairInterpretability2607.05250
22make agents use tools and reusable skills more reliablyTraining and Post-training2607.05196
23make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2607.05189
24improve model reasoning, planning, and verificationMultimodal Models2607.05180
25make agents use tools and reusable skills more reliablyCode Intelligence2607.05139
26make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2607.05077