2026-06-16

Internal Generation Record

Internal generation metadata: 302 candidate papers.

Published 2026-06-16 Target source 2026-06-14 Actual source 2026-06-12 Candidates 302 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 2026-06-15T23:07:45.626637+00:00. Generated at 2026-06-15T23:08:25.939902+00:00. Machine-readable details stay under data/processed and data/reports.

Selected papers

RankTakeawayTopicarXiv
1improve code generation, execution feedback, and automated repairRobotics and Embodied AI2606.14042
2make agents use tools and reusable skills more reliablyCode Intelligence2606.14594
3make agents use tools and reusable skills more reliablyAgents and Tool Use2606.14589
4make agents use tools and reusable skills more reliablyCode Intelligence2606.14445
6make RAG retrieval and knowledge-base QA more reliableBenchmarks and Evaluation2606.14466
11make RAG retrieval and knowledge-base QA more reliableVideo Generation2606.14096
5make agents use tools and reusable skills more reliablyAgents and Tool Use2606.14654
7make agents use tools and reusable skills more reliablyAgents and Tool Use2606.14357
8make agents use tools and reusable skills more reliablyAgents and Tool Use2606.14327
9improve code generation, execution feedback, and automated repairBenchmarks and Evaluation2606.14278
10improve code generation, execution feedback, and automated repairCode Intelligence2606.14210
12make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2606.14027
13test temporal consistency and motion realism in video generationBenchmarks and Evaluation2606.14579
14make agents use tools and reusable skills more reliablySafety and Alignment2606.14517
15make RAG retrieval and knowledge-base QA more reliableRetrieval and RAG2606.14164
16improve model reasoning, planning, and verificationTraining and Post-training2606.14142
17improve code generation, execution feedback, and automated repairMultimodal Models2606.14125
18improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.14119
19improve model reasoning, planning, and verificationBenchmarks and Evaluation2606.14697
20improve model reasoning, planning, and verificationTraining and Post-training2606.14694
21improve model reasoning, planning, and verificationMultimodal Models2606.14691
22improve image generation, visual understanding, and controllable renderingTraining and Post-training2606.14684
23make agents use tools and reusable skills more reliablyBenchmarks and Evaluation2606.14571
24improve code generation, execution feedback, and automated repairData Engineering2606.14518
25make agents use tools and reusable skills more reliablyAgents and Tool Use2606.14502
26make RAG retrieval and knowledge-base QA more reliableTraining and Post-training2606.14475