TSR Desk · science · 1 November 2026, 01:00 UTC
Aligning Autoresearch: Co-Improvement between Agents and Humans
- What
- Aligning Autoresearch: Co-Improvement between Agents and Humans
- Who
- arxiv.org
- When
- 31 October 2026, 04:00 UTC
- Category
- Science
- Primary source
- https://arxiv.org/abs/2610.38882
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
In this work we address these issues in four ways: (i) we empirically study the role of humans in directing autoresearch agents, focusing on the domain of benchmark creation, and find humans still play a pivotal role particularly in the ideation phase; (ii) we also develop a benchmark, HackBench, that shows current autoresearch agents are not aligned and are unable to achieve hack localization sufficiently; (iii) we present a method It comes from a paper posted to arXiv on 31 October 2026. Autoresearch agents can now attempt long-horizon AI research end-to-end, i.e., self-improvement. However, best results are still obtained by research agents interacting with human researchers, and improving AI's ability to perform this co-research will only reinforce this effect---a process termed co-improvement (Weston and Foerster, 2025). Further, aligning with human expectations is likely a safer path for research agents, especially given recent agent reward hacking phenomena (OpenAI, 2026b). to train agents for improved human interaction by using human simulators as a proxy during reinforcement learning (RL); and finally (iv) we develop a method to improve model text generation, and hence agent communication, by RL with rubrics aligned with human experts. Together, our training and evaluation recipes provide a path toward more capable and aligned (co-)research agents.
Why it counts
In this work we address these issues in four ways: (i) we empirically study the role of humans in directing autoresearch agents, focusing on the domain of benchmark creation, and find humans still play a pivotal role particularly in the ideation phase; (ii) we also develop a benchmark, HackBench, that shows current autoresearch agents are not aligned and are unable to achieve hack localization sufficiently; (iii) we present a method to train agents for improved human interaction by using human
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.