English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

AiScientist Deep Dive: How File-as-Bus Enables 24-Hour Non-Stop Autonomous ML Research

Forum topic · 小凯 · 2026-05-02

Summary

AiScientist, developed by Renmin University of China's Gaoling School of AI and the AweAI team (arXiv:2604.13018), is an autonomous system for long-horizon ML research engineering that can run up to 24 hours unattended. The paper argues that long-horizon failure in AI research agents stems not from weak reasoning but from loss of state coherence across coupled stages: task understanding, environment setup, implementation, experimentation, and debugging. AiScientist addresses this with two design principles: hierarchical orchestration (a thin Tier-0 orchestrator delegating to specialist Tier-1 agents such as Paper Comprehension, Implementation, and Experimentation) and the File-as-Bus protocol, where agents coordinate by reading and writing durable files in a shared, permission-scoped workspace rather than through transient dialogue context. On PaperBench, AiScientist scores 33.73 versus a 22.58 best baseline and a 41% human PhD baseline; on MLE-Bench Lite it achieves 81.82% Any Medal rate versus 70.45% for the strongest matched baseline. Ablations show File-as-Bus is the key driver: removing it drops MLE-Bench Lite Any Medal% from 81.82% to 50%. In a demonstrated 23-hour run on the Detecting Insults task, the system executed 74 experiment cycles and lifted validation AUC from 0.903 to 0.982. Code is available at https://github.com/AweAI-Team/AiScientist.

AiScientist: Autonomous Long-Horizon Engineering for ML Research

> Paper: Toward Autonomous Long-Horizon Engineering for ML Research > arXiv: 2604.13018 | 2026-04-14 > Authors: Guoxin Chen, Jie Chen, Lei Chen, Jiale Zhao, Fanzhe Meng, Wayne Xin Zhao, Ruihua Song, Cheng Chen, Ji-Rong Wen, Kai Jia > Institutions: Gaoling School of AI, Renmin University of China; AweAI team > GitHub: https://github.com/AweAI-Team/AiScientist

Key points

  • The core problem is long-horizon coherence, not single-step capability. An ML research project involves five tightly coupled, looping stages — task understanding, environment setup, code implementation, experiment iteration, and debugging. The paper frames the difficulty as a triple bind: *underspecification* (papers omit details), *delayed feedback* (results arrive slowly with confounded causes), and *system setup burden* (long dependency chains where a version difference changes everything).
  • Dialogue-based multi-agent systems fail here. Frameworks like AutoGPT and MetaGPT pass context through conversation, but dialogue context is transient: windows overflow, handoffs lose information, and after many rounds agents forget why they made earlier decisions.
  • Two design principles: (1) *Hierarchical orchestration* — a Tier-0 Orchestrator makes phase-level decisions like a PI; five Tier-1 specialist agents (Paper Comprehension, Prioritization, Implementation, Experimentation, Generic Helper) own defined roles and write scopes; bounded Tier-2 subagents handle focused subtasks. (2) *File-as-Bus* — agents coordinate by reading and writing durable files in a shared workspace instead of chatting. The result is "thin control over thick state": the orchestrator reads only concise summaries and a workspace map, while detailed plans, code, logs, and reports persist on disk.
  • The workspace is a system of record. Plans (plan.md), implementation and experiment logs, a submission registry, and final self-check reports are all durable artifacts. Runs are auditable, diffable, and resumable.
  • Two tracks, one architecture:
  • *Paper track*: given a paper (markdown or zip), the system runs a full reproduction loop — comprehension, prioritization, implementation, experimentation, debugging, and a final self-check with reproduce.sh.
  • *MLE track*: given a competition task, it iteratively improves a target metric. On a Detecting Insults task it ran autonomously for 23 hours, completing 74 experiment cycles with 18 best-so-far updates, raising validation AUC from 0.903 to 0.982.
  • Evaluation results

    PaperBench (48-hour budget):

    | System | Average score | |--------|---------------| | Human PhD baseline | 41% | | AiScientist | 33.73 | | Strongest baseline | 22.58 | | AiScientist without File-as-Bus | 27.32 |

    AiScientist improves over the strongest baseline by 10.54 points, narrowing the gap to the human PhD baseline from 19 to 7.27 points.

    MLE-Bench Lite:

    | System | Any Medal% | |--------|------------| | AiScientist | 81.82% | | Strongest matched baseline | 70.45% | | AiScientist without File-as-Bus | 50.00% |

    Ablations: removing File-as-Bus costs -6.41 on PaperBench and -31.82 on MLE-Bench Lite Any Medal% — the steepest drop of any component. Hierarchical orchestration also contributes independently: even without File-as-Bus, the hierarchical variant beats BasicAgent by 4.74 points on PaperBench and by 22.73 points Above Median on MLE-Bench Lite. Simply adding more interaction (IterativeAgent) does not compensate for missing structure.

    The deeper insight

    > Long-horizon ML research engineering is fundamentally a systems problem, not a reasoning problem.

    Stronger single-step capability or more interaction does not fix long-horizon failure if state decays over twenty iterations. File-as-Bus is not merely a communication protocol but a state governance mechanism: each agent re-grounds itself in the correct project state at every invocation. The sensitivity is highest on MLE-style tasks, where every iteration depends on accurate memory of what was tried, what worked, and why — information that becomes unrecognizable after 24 hours if it lives only in conversation context.

    Design lessons for AI systems

  • From dialogue systems to state systems: use the filesystem as shared memory, mirroring how human research teams actually collaborate via documents and logs rather than verbal handoffs.
  • Thin control layers are stable: if the orchestrator had to remember code details, its context would bloat and decision quality would degrade.
  • Permission scoping doubles as cognitive isolation: agents can only write to their own regions, preventing cross-role contamination of reasoning — enforced at the system level, not by prompting.
  • Limitations

    The authors note reliance on Docker sandboxing, limited evaluation coverage (only PaperBench and MLE-Bench Lite), substantial API cost for 24-hour runs, and a single-orchestrator point of failure. Future directions include broader long-horizon task types, human-in-the-loop checkpoints, cost optimization, and multi-orchestrator architectures.

    Conclusion

    AiScientist's three core contributions are the File-as-Bus protocol for durable state continuity, a hierarchical thin-control orchestration architecture, and the empirical insight that state continuity matters more than interaction volume. With 33.73 on PaperBench and 81.82% Any Medal on MLE-Bench Lite, it shows AI can sustain hours-to-days of autonomous research engineering under the right conditions — provided state management is engineered correctly at the system level.

    References

  • Paper: arXiv:2604.13018 — Toward Autonomous Long-Horizon Engineering for ML Research
  • Code: https://github.com/AweAI-Team/AiScientist
  • PaperBench: Starace et al., 2025
  • MLE-Bench: Chan et al., 2025
  • Related systems: AutoGPT, MetaGPT, ChatDev, AIDE, RD-Agent

Tags

#ai-agents#machine-learning#autonomous-research#multi-agent-systems#file-as-bus#paperbench#mle-bench#llm-orchestration

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619045