Agentic AI and coding with AI papers

Recent papers on Agentic AI & harness engineering

Year.Mon	Link	Description
19.11	https://arxiv.org/abs/1911.01547	Francois Chollets introduces the reasoning challenge
22.10	https://arxiv.org/abs/2210.03629	ReAct paper
23.10	https://arxiv.org/abs/2310.08560	MemGPT paper: memory for agents
24.10	https://arxiv.org/abs/2410.10813	Benchmark for memory
25.07	https://arxiv.org/abs/2507.19457	GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning. prompt-engineering followup on DSPy
25.03	https://arxiv.org/abs/2503.22625
25.12	https://arxiv.org/abs/2512.24601v1
2025	https://www.kaggle.com/whitepaper-agents	Google Whitepaper Agents:
25.06	https://arxiv.org/abs/2506.08945
25.12	https://arxiv.org/abs/2512.24601
26.01	https://arxiv.org/abs/2601.20245
26.05	https://arxiv.org/abs/2605.09998	Continual Harness paper
26.07	https://www.kaggle.com/whitepaper-the-new-SDLC-with-vibe-coding	Google Whitepaper How agents shape the new Software Development Life Cycle
26.07	https://arxiv.org/abs/2606.24937	Nice overview paper of Agentic AI
26.07	https://arxiv.org/abs/2607.20064	Harness for ARC-AGI 3
26.07	https://arxiv.org/abs/2607.13104	Schmidthuber’s overview paper of self improvements
26.08	https://arxiv.org/abs/2608.23552