AI Research Brief

Source-first daily briefs for AI papers worth tracking.

Daily updates · Bilingual notes · Traceable sources

Latest issue · 2026-09-30

Make agents use tools and reusable skills more reliably, Improve model reasoning, planning, and verification

Today tracks: make agents use tools and reusable skills more reliably, make agents use tools and reusable skills more reliably, improve model reasoning, planning, and verification.

Target 2026-09-28 Actual 2026-09-28 999 candidates 6 featured 20 tracked

Featured

1 When Does Structured Knowledge Help Neural Theorem Proving?↗
2 eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models↗
3 Imprint Reader: From Weight-Update Readout to Behavioral Intervention↗
4 Improving Large Language Models for Code through Runtime Program-State Reasoning↗
5 Denoising Multi-Robot Trajectories↗
6 Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline↗

English brief 中文简报 Source page

Recent Issues

Publication order follows the generated brief order.

Full archive

2026-09-29

Make agents use tools and reusable skills more reliably, Improve code generation, execution feedback, and automated repair

Today tracks: make agents use tools and reusable skills more reliably, make agents use tools and reusable skills more reliably, improve code generation, execution feedback, and automated repair.

444 candidates Source 2026-09-25 Read ZH

2026-09-28

Improve model reasoning, planning, and verification, Make agents use tools and reusable skills more reliably, Make RAG retrieval and knowledge-base QA more reliable

Today tracks: improve model reasoning, planning, and verification, make agents use tools and reusable skills more reliably, make RAG retrieval and knowledge-base QA more reliable.

497 candidates Source 2026-09-24 Read ZH

2026-09-27

Make RAG retrieval and knowledge-base QA more reliable, Improve code generation, execution feedback, and automated repair, Make agents use tools and reusable skills more reliably

Today tracks: make RAG retrieval and knowledge-base QA more reliable, improve code generation, execution feedback, and automated repair, make agents use tools and reusable skills more reliably.

497 candidates Source 2026-09-24 Read ZH

2026-09-26

Make agents use tools and reusable skills more reliably, Improve model reasoning, planning, and verification

Today tracks: make agents use tools and reusable skills more reliably, improve model reasoning, planning, and verification, make agents use tools and reusable skills more reliably.

497 candidates Source 2026-09-24 Read ZH

2026-09-25

Make RAG retrieval and knowledge-base QA more reliable, Improve code generation, execution feedback, and automated repair, Improve model reasoning, planning, and verification

Today tracks: make RAG retrieval and knowledge-base QA more reliable, improve code generation, execution feedback, and automated repair, improve code generation, execution feedback, and automated repair.

406 candidates Source 2026-09-23 Read ZH

2026-09-24

Make agents use tools and reusable skills more reliably, Identify and reduce safety, jailbreak, and alignment risks, Make RAG retrieval and knowledge-base QA more reliable

Today tracks: make agents use tools and reusable skills more reliably, identify and reduce safety, jailbreak, and alignment risks, make RAG retrieval and knowledge-base QA more reliable.

414 candidates Source 2026-09-22 Read ZH

Topics

Built from existing tags/topics only.

View all

Agents and Tool Use

120 related briefs

Reasoning and Planning

67 related briefs

Training and Post-training

120 related briefs

Retrieval and RAG

102 related briefs

Multimodal Models

106 related briefs

Code Intelligence

86 related briefs

Vision and Image Generation

48 related briefs

Video Generation

80 related briefs

Safety and Alignment

55 related briefs

Reading Boundary

This project generates briefs from public arXiv metadata and public signals for research tracking and discovery. Original papers remain the source of record.