Designing Informative Actions: Action Construction for Long-Horizon Research Agents
cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Accelerating scientific discovery with Co-Scientist
- Kosmos: An AI Scientist for Autonomous Discovery
- MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
- FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
- InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
- OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
- AgentBench: Evaluating LLMs as Agents
- Exploration and Exploitation Errors Are Measurable for Language Model Agents
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
- Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents