Paper

ACC: Compiling Agent Trajectories for Long-Context Training

Unreadunread

AI summary

arXiv:2605. 21850v1 Announce Type: new Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs.

Reading status

Priority

About this paper

Authors: Qisheng Su, Zhen Fang, Shiting Huang, Yu Zeng, Yiming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Zehui Chen, Lijun Wu, Feng Zhao
Released: 2026-05-22 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because ACC: Compiling Agent Trajectories for Long-Context Training 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: text, rect, soft, eval, without, trained, contexts, model. Source: arxiv cs.CL (NLP).
arXiv: 2605.21850

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to ACC: Compiling Agent Trajectories for Long-Context Training. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.