Jilin University

Headlines · 3

1. 10h
   SkillPoison Uses Successful Experiences to Poison Agent Skills

   A report on research by a Jilin University team describes SkillPoison, an attack that does not inject malicious instructions into an AI agent's skill library. It selects successful, validated experiences, adds attribution annotations, and repeats them across task categories, encouraging a skill extractor to generalize a locally valid rule while dropping its preconditions. The evaluation covered three datasets, two skill-formation frameworks, and one victim model, with an attack budget of 15 successful experiences. The reported peak attack success rate was 95.71%; in that experiment, task accuracy fell from 78.57% to 3.81%. The evaluation did not test carefully controlled low-and-slow attacks, and performance with stronger models or more complex commercial skill pipelines remains unknown.

   掘金 · 人工智能 · 🔥 4
2. Oct 20
   HKUST-led team's HeLa-Mem links distant memories for AI agents

   Researchers from HKUST (Guangzhou), Jilin University and the Chinese University of Hong Kong have proposed HeLa-Mem (Hebbian Learning Associative Memory), which targets the gap where an AI agent's relevant memories share little wording, and the paper was accepted to ACL 2026 Main with code published on GitHub. Each dialogue turn becomes an episodic memory node; links between nodes strengthen when they are retrieved together and decay when unused, while a reflection agent distils reusable semantic memory from densely connected nodes and flags isolated, stale nodes as forgetting candidates. Retrieval runs both a similarity/keyword/time path and an association-spreading path, merging results with semantic memory for the LLM; on LoCoMo with GPT-4o-mini, the authors report F1 of 40.14 (multi-hop), 47.29 (temporal), 29.70 (open-domain) and 51.89 (single-hop), using about 1010 retrieval-context tokens on average, versus roughly 2000 cited for MemoryOS and about 16910 for full-dialogue input. The authors note association weights must accumulate through interaction, leaving a cold-start challenge when history is thin, and that the distilled knowledge depends on the base LLM's capability.

   36氪 人工智能 · 🔥 0
3. Oct 7
   2026 Nobel Chemistry Prize goes to Kagan and Soai for asymmetric autocatalysis

   The Royal Swedish Academy of Sciences awarded the 2026 Nobel Prize in Chemistry to Henri B. Kagan of Paris-Sud University and Kenso Soai of Tokyo University of Science for discovering nonlinear effects and autocatalysis in asymmetric organic synthesis. Kagan, 95, was widely seen as having missed out on the prize in 2001; Soai's eponymous reaction is credited with producing near-single-handed chirality from achiral starting materials, a result linked to the origin of biological homochirality. The work is described as an everyday tool for chiral drug, flavour and agrochemical synthesis.

   量子位（原生 RSS） · 🔥 0

Experience and discussion from the community

Share my Jilin University experienceAsk about Jilin University