Scaling Scientific Discovery Environments for Turn-Level Agentic RL
Quick Answer
The paper presents SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments, achieving state-of-the-art results on hypothesis-driven scientific data analysis benchmarks with the SciDisco-14B model.
Quick Take
This framework enhances long-horizon scientific analysis by compiling hypotheses, datasets, and verifiers into interactive environments, enabling turn-level credit assignment for actions that yield verifiable evidence.
Key Points
- SciDisco enables training in environments where analytical progress can be verified.
- DAG-grounded trajectory synthesis constructs multi-turn demonstrations filtered by verifiers.
- DiscoPO assigns turn-level credit to actions producing verifiable analytical evidence.
- SciDisco-14B achieves state-of-the-art performance on scientific data analysis benchmarks.
Paper Resources
Source Excerpt
agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim. Long-horizon scientific analysis remains constrained by the lack of process supervised environments over real-world scientific data. This paper introduces SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments. SciThèque compiles hypotheses, datasets, hi
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.