AI 업계의 최신 소식을 빠르게 확인하세요.
arXiv:2604.21937v1 Announce Type: new Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multistep workflows, yet current AI agents struggle to maintain robust performance and...
arXiv:2604.21965v1 Announce Type: new Abstract: Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce results given only a paper's methods description and original data?
arXiv:2604.22026v1 Announce Type: new Abstract: AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peerreview standards for quality and novelty.
arXiv:2604.22080v1 Announce Type: new Abstract: LLMbased agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise.
arXiv:2604.22085v1 Announce Type: new Abstract: The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems.
arXiv:2604.22119v1 Announce Type: new Abstract: As reasoning capacity and deployment scope grow in tandem, large language models LLMs gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks ESRRs.
arXiv:2604.22273v1 Announce Type: new Abstract: Iterative selfcorrection is widely used in agentic LLM systems, but when repeated refinement helps versus hurts remains unclear.
arXiv:2604.22411v1 Announce Type: new Abstract: Even when decoding with temperature $T=0$, large language models LLMs can produce divergent outputs for identical inputs.
Learn how Symphony, an opensource spec for Codex orchestration, turns issue trackers into alwayson agent systems—boosting engineering output and reducing context switching.
How Choco used OpenAI APIs to streamline food distribution, boost productivity, and unlock growth—an indepth customer story on realworld AI impact.
How to build scalable web apps with OpenAI's Privacy Filter
기술을 토대로 인류의 더 나은 삶에 기여하고자 하는 현대자동차·기아의 노력이 세계인의 마음을 사로잡았다.현대자동차·기아는 세계 최고 권위의 국제 광고제 ‘원쇼The One Show’와 ‘스파이크아시아Spikes Asia’에서 ‘비전 펄스Vision Pulse’ 기술 캠페인이 각각 본상 두 건과 동상을 수상했다고 26일 밝혔다현대차·기아는 세계 최고 권위의 국제 광고제 ‘원쇼The One Show’와 ‘스파이크아시아Spikes Asia’에서 ‘비전 펄스Vision Pulse’ 기술 캠페인이 각각 본상 두 건과 동