๋ณธ๋ฌธ์œผ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

Topic: #ai-agents

A collection of 14 posts about ai-agents.

NTU ํ•˜ํŽธ 46โ€“50์ชฝ์„ ๋”ฐ๋ผ SEAL์˜ ์ž๊ธฐ ํŽธ์ง‘ ๋ณด์ƒ, ๋‘ ํ•™์Šต ์‹œ๊ฐ„ ์ฒ™๋„, ํ•™์Šต๋œ ์ตœ์ ํ™”๊ธฐ์™€ MAML์„ ์‚ดํŽด๋ณธ๋‹ค. ์‹ ํ’€์ด ์ผ๊ณฑ ๊ฐœ๋กœ ๋ชจ๋ธ๊ณผ ํ•™์Šต ๊ทœ์น™์˜ ๊ฐฑ์‹ ์„ ๊ตฌ๋ถ„ํ•œ๋‹ค.

15 min read
#self-improvement#ai-agents#prompt-optimization
๐Ÿ‡ฐ๐Ÿ‡ท ko

NTU ํ•˜ํŽธ 41โ€“45์ชฝ์˜ ์‹ ํ’€์ด 7๊ฐœ๋กœ ๊ฒฝ์‚ฌํ•˜๊ฐ•๋ฒ•, PostTrainBench, autoresearch, AlphaEvolve์™€ ShinkaEvolve๋ฅผ ์ฝ๋Š”๋‹ค. ๊ฐ€์ค‘์น˜ ํ•œ ๋ฒˆ์˜ ๊ฐฑ์‹ ์—์„œ ํ•™์Šต ๊ทœ์น™ ์ž์ฒด์˜ ํ‰๊ฐ€๊นŒ์ง€ ๊ณ„์‚ฐํ•œ๋‹ค.

14 min read
#self-improvement#ai-agents#prompt-optimization
๐Ÿ‡ฐ๐Ÿ‡ท ko

NTU ํ•˜ํŽธ 36โ€“40์ชฝ์„ ๋”ฐ๋ผ ํ•˜๋„ค์Šค๊ฐ€ ๋‹ค์Œ ํŽธ์ง‘์ž๊ฐ€ ๋˜๋Š” ๊ณผ์ •์„ ์ฝ๋Š”๋‹ค. ์‹ ํ’€์ด ์ผ๊ณฑ ๊ฐœ๋กœ Hyperagents์˜ ๋ถ€๋ชจ ์„ ํƒ ์‹คํ—˜๊ณผ Learning to Self-Evolve์˜ ๋ฌธ๋งฅ ํŽธ์ง‘ ๋ณด์ƒ์„ ๊ณ„์‚ฐํ•œ๋‹ค.

15 min read
#self-improvement#ai-agents#prompt-optimization
๐Ÿ‡ฐ๐Ÿ‡ท ko

NTU ํ•˜ํŽธ 31โ€“35์ชฝ์„ ์ฝ์œผ๋ฉฐ ํ•˜๋„ค์Šค๋ฅผ ๋ฐ”๊ฟ€ ๋•Œ ์ƒ๊ธฐ๋Š” ๋ง๊ฐ๊ณผ ๊ฐœ์„ ๊ธฐ์˜ ์—ญํ• ์„ ์‚ดํŽด๋ณธ๋‹ค. ๊ฐ€์ค‘์น˜๋ฅผ ๊ณ ์ •ํ•ด๋„ ์˜ˆ์ „ ๋Šฅ๋ ฅ์ด ๋–จ์–ด์ง€๋Š” ์ด์œ , ์„ฑ๊ณต๋ฅ ๊ณผ ์œ ์ง€์œจ์˜ ๋ถ„๋ชจ, DGM์˜ ํŽธ์ง‘์ž ๊ณ ์ • ์‹คํ—˜์„ ์—ฌ์„ฏ ๊ณ„์‚ฐ ์˜ˆ์ œ๋กœ ํ‘ผ๋‹ค.

13 min read
#self-improvement#ai-agents#prompt-optimization
๐Ÿ‡ฐ๐Ÿ‡ท ko

NTU 2026 ํ•˜ํŽธ 21โ€“25์ชฝ์„ ํ•œ ์žฅ์”ฉ ์ฝ๋Š”๋‹ค. ExpRAG์˜ ๊ฒฝํ—˜ ๊ฒ€์ƒ‰๊ณผ Fine-tuning, BetterTogether์˜ ๊ต๋Œ€ ์ตœ์ ํ™”, E-SPL์˜ ํ”„๋กฌํ”„ํŠธ ์ง„ํ™”์™€ ๊ฐ•ํ™”ํ•™์Šต, ๋ชฉํ‘œ ๋ณ€ํ™” ์‹œ ์žฌํ‰๊ฐ€๋ฅผ ๊ณต์‹ ๋…ผ๋ฌธ ๋ฐ Omar Khattab ๊ฐ•์˜๋กœ ํ•ด์„คํ•œ๋‹ค.

16 min read
#self-improvement#ai-agents#prompt-optimization
๐Ÿ‡ฐ๐Ÿ‡ท ko

NTU ์ž๊ฐ€๊ฐœ์„  AI ํ•˜ํŽธ 16โ€“20์ชฝ์„ ์›๋ณธ ์Šฌ๋ผ์ด๋“œ ํ•œ ์žฅ์”ฉ ์ฝ๋Š”๋‹ค. DGM ์•„์นด์ด๋ธŒ์™€ ํƒ์ƒ‰ ๊ณ„๋ณด, DSPy์˜ ์„ ์–ธํ˜• ํ”„๋กœ๊ทธ๋žจ๊ณผ ์ž๋™ ์ตœ์ ํ™”, ํ•˜๋„ค์Šคยท๋ชจ๋ธ ํŒŒ๋ผ๋ฏธํ„ฐ์˜ ๊ฒฝ๊ณ„, ๊ฒฝํ—˜ ๊ฒ€์ƒ‰๊ณผ fine-tuning์„ ๋…ผ๋ฌธ๊ณผ ์™ธ๋ถ€ ๊ฐ•์˜ ์ž๋ฃŒ๋กœ ๋ณด๊ฐ•ํ•œ๋‹ค.

14 min read
#self-improvement#ai-agents#dspy
๐Ÿ‡ฐ๐Ÿ‡ท ko

ํ•˜ํŽธ 11โ€“15์ชฝ์˜ OPROยทGEPAยทALMAยทDarwin Gรถdel Machine์„ ํ•œ ์žฅ์”ฉ ์ฝ๋Š”๋‹ค. CMUยทStanford ๋ฐœํ‘œ ์Šฌ๋ผ์ด๋“œ์™€ GEPA ์ €์ž์˜ ์˜์ƒ ์„ค๋ช…์„ ์—ฐ๊ฒฐํ•ด ํ”„๋กฌํ”„ํŠธ ํƒ์ƒ‰, ๋ฌธํ•ญ๋ณ„ ํ›„๋ณด ์„ ํƒ, ๋ฉ”๋ชจ๋ฆฌ ์„ค๊ณ„์™€ ์ฝ”๋“œ ์ž๊ธฐ์ˆ˜์ •์˜ ์›๋ฆฌยท๊ณ„์‚ฐ ์˜ˆยทํ‰๊ฐ€ ์กฐ๊ฑด์„ ์„ค๋ช…ํ•œ๋‹ค.

24 min read
#self-improvement#prompt-optimization#ai-agents
๐Ÿ‡ฐ๐Ÿ‡ท ko

ํ•˜ํŽธ 6โ€“10์ชฝ์—์„œ ๋ชจ๋ธ ๊ฐ€์ค‘์น˜์™€ ํ•˜๋„ค์Šค๋ฅผ ๊ตฌ๋ถ„ํ•˜๊ณ , ํ”„๋กฌํ”„ํŠธยท๋„๊ตฌยท์‹คํ–‰ ํ๋ฆ„์„ ์ˆ˜์ •ํ•˜๋Š” ์›๋ฆฌ๋ฅผ ์‚ดํŽด๋ณธ๋‹ค. CMUยทNAIRRยทMIT ๊ฐ•์˜์™€ SWE-agentยทDSPyยทAFlowยทฯ„-bench๋ฅผ ์—ฐ๊ฒฐํ•ด ๊ธฐ์–ต ๊ด€๋ฆฌ, ํ›„๋ณด ์ƒ์„ฑ, ๊ณต์ •ํ•œ ๋น„๊ต, ๋น„์šฉ๊ณผ ๋ฐ˜๋ณต ์‹ ๋ขฐ์„ฑ์„ ์„ค๋ช…ํ•œ๋‹ค.

24 min read
#self-improvement#ai-agents#harness
๐Ÿ‡ฐ๐Ÿ‡ท ko

AI ์—์ด์ „ํŠธ๋ฅผ ๋ชจ๋ธ ๊ฐ€์ค‘์น˜, ํ•˜๋„ค์Šค, ์‹คํ–‰ ์ƒํƒœ๋กœ ๋‚˜๋ˆ„๊ณ  ReActยทGenerative AgentsยทReflexionยทSWE-agent์˜ ๊ตฌ์กฐ๋ฅผ ํ†ตํ•ด ๋„๊ตฌ์™€ ๋ฉ”๋ชจ๋ฆฌ๊ฐ€ ํ–‰๋™์„ ๋ฐ”๊พธ๋Š” ์›๋ฆฌ์™€ ๊ณต์ •ํ•œ ๊ฐœ์„  ํ‰๊ฐ€๋ฅผ ์‚ดํŽด๋ณธ๋‹ค.

14 min read
#self-improvement#ai-agents#harness
๐Ÿ‡ฐ๐Ÿ‡ท ko

์™„์„ฑ๋œ ๋ณ‘๋ ฅ ์š”์•ฝ์„ ํ‘ธ๋Š” ๋Œ€์‹  ์งˆ๋ฌธ๊ณผ ๊ฒ€์‚ฌ๋ฅผ ์ฐจ๋ก€๋กœ ๊ณ ๋ฅด๊ฒŒ ํ•œ Science ์—ฐ๊ตฌ๋ฅผ ํ†ตํ•ด 83.2% ์ •ํ™•๋„์˜ ์˜๋ฏธ์™€ ์ž„์ƒ ์ ์šฉ ์ „ ๊ฒ€์ฆ ๊ณผ์ œ๋ฅผ ์‚ดํ•€๋‹ค.

7 min read
#frontier-one#clinical-ai#diagnostic-reasoning
๐Ÿ‡ฐ๐Ÿ‡ท ko

LEASH๊ฐ€ ์ˆจ์€ ์ƒํƒœ์˜ ๋ถˆํ™•์‹ค์„ฑ์œผ๋กœ ์ปดํ“จํ„ฐ ์‚ฌ์šฉ ์—์ด์ „ํŠธ๋ฅผ ์„ ํƒ์ ์œผ๋กœ ์ƒํ–ฅํ•˜๊ณ , OSWorld์˜ ๋น„์šฉยท์„ฑ๊ณต๋ฅ ์„ ๋งž๋ฐ”๊พผ ์‚ฌ์ „๋…ผ๋ฌธ ๊ฒฐ๊ณผ์™€ ๊ฒ€์ฆ ๊ณต๋ฐฑ์„ ์‚ดํ•€๋‹ค.

7 min read
#frontier-candidate#ai-agents#uncertainty
๐Ÿ‡ฐ๐Ÿ‡ท ko

Google Research๊ฐ€ ์‹คํ—˜์‹ค ์ƒํƒœ ์ถ”์ ยท์‹œ๋ฎฌ๋ ˆ์ด์…˜ยท์‹คํ–‰ ๋กœ๊ทธ๋ฅผ ๊ฒฐํ•ฉํ•ด AI ์—์ด์ „ํŠธ์˜ ์•ก์ฒด ์ทจ๊ธ‰ ์˜ค๋ฅ˜๋ฅผ ์žก๊ณ  ์Šค์Šค๋กœ ์‹คํ—˜์„ ๊ณ ์นœ ์ดˆ๊ธฐ ๊ฒฐ๊ณผ๋‹ค.

7 min read
#frontier-candidate#lab-automation#ai-agents
๐Ÿ‡ฐ๐Ÿ‡ท ko

AI๊ฐ€ ์ดˆ์•ˆ์„ ์“ฐ๋Š” ์ผ๊ณผ ๋ฏฟ๊ณ  ์ฝ์„ ์ˆ˜ ์žˆ๋Š” ๊ธ€์„ ๊ณต๊ฐœํ•˜๋Š” ์ผ์€ ๋‹ค๋ฆ…๋‹ˆ๋‹ค. ๋…์ž์˜ ์งˆ๋ฌธ์—์„œ ์ถœ๋ฐœํ•ด ์›๋ฌธยท์ˆ˜์‹ยท๊ทธ๋ฆผ ๊ฒ€์ฆ, ๋ณ‘๋ ฌ ๊ฒ€ํ† ์™€ ๋ฒ„์ „ ๊ด€๋ฆฌ, ์Šน์ธ๊ณผ ๊ณต๊ฐœ ํ™•์ธ์œผ๋กœ ์ด์–ด์ง€๋Š” JJo์˜ ์šด์˜ ๊ณผ์ •์„ ์„ค๋ช…ํ•ฉ๋‹ˆ๋‹ค. ์‹ค์ œ๋กœ ํ™•์ธํ•œ ๋ฒ”์œ„์™€ ํด๋ผ์šฐ๋“œยทBlogger ์—ฐ๊ฒฐ์— ๋‚จ์€ ๊ณผ์ œ๋„ ๊ตฌ๋ถ„ํ•ฉ๋‹ˆ๋‹ค.

11 min read
#ai-agents#technical-writing#publishing-workflow
๐ŸŒ ko-KR

OpenAI๊ฐ€ ๊ณต๊ฐœํ•œ ์—ฐ๊ตฌ ์ž๋™ํ™” ๋ฐ์ดํ„ฐ๋ฅผ ๊ณต๋Œ€์ƒ์˜ ๋ˆˆ๋†’์ด๋กœ ์ฝ๋Š”๋‹ค. AI ์—์ด์ „ํŠธ์˜ ์—ญํ• ๋ถ€ํ„ฐ ์‹คํ–‰์‹œ๊ฐ„๊ณผ ์ƒ์‚ฐ์„ฑ์˜ ์ฐจ์ด, ๋ณ‘๋ ฌํ™”์˜ ํ•œ๊ณ„, ์‚ฌ๋žŒ ๊ฐœ์ž…๊ณผ ์„ฑ๊ณต๋ฅ ์˜ ๋ถ„๋ชจ๊นŒ์ง€ ์ˆ˜์‹๊ณผ ์›๋ณธ ๋„์‹์œผ๋กœ ํ•ด์„คํ•œ๋‹ค.

12 min read
#frontier-one#ai-agents#research-automation
๐Ÿ‡ฐ๐Ÿ‡ท ko