Paper

From I/O to Code with Discovery Agent

Unreadunread

AI summary

arXiv:2605. 15334v1 Announce Type: new Abstract: The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science.

Reading status

Priority

About this paper

Authors: Yihong Dong, Jiaru Qian, Haoran Zhang, Peixu Wang, Binhua Li, Zhi Jin, Yongbin Li, Ge Li, Xiaokang Yang, Xue Jiang
Released: 2026-05-18 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because From I/O to Code with Discovery Agent overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, latin, rect, under, alignment, correct, line, rate. Source: arxiv cs.LG (Machine Learning).
arXiv: 2605.15334

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to From I/O to Code with Discovery Agent. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.