Paper

BAGEN: Are LLM Agents Budget-Aware?

Unreadunread

AI summary

arXiv:2606. 00198v1 Announce Type: new Abstract: While agents are increasingly spending more resources, today agent cost is mostly measured only after execution.

Reading status

Priority

About this paper

Authors: Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan, Longju Bai, Junyao Zhang, Xing Jin, Boshan Chen, Jinyan Su, Xingyao Wang, Jiaxin Pei, Manling Li
Released: 2026-06-02 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because BAGEN: Are LLM Agents Budget-Aware? 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: strong, source, token, project, control, completion, model. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.00198

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to BAGEN: Are LLM Agents Budget-Aware?. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.