Episode
ACC: Compiling Agent Trajectories for Long-Context Training
- Podcast
- Daily Paper Cast
- Published
- May 23, 2026
- Duration seconds
- 1485
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/09dad681
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/acc-compiling-agent-trajectories-for-long-context-training/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/acc-compiling-agent-trajectories-for-long-context-training.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 53 | cs.CL, cs.AI Authors: Qisheng Su, Zhen Fang, Shiting Huang, Yu Zeng, Yiming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Zehui Chen, Lijun Wu, Feng Zhao Title: ACC: Compiling Agent Trajectories for Long-Context Training Arxiv: http://arxiv.org/abs/2605.21850v1 Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph t…