# Accelerating Scientific Discovery with Autonomous Goal-evolving Agents arXiv: https://arxiv.org/abs/2512.21782 ยท HTML: https://mlsanity.com/paper/2512.21782/ ## Key facts - Cited by 19 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 12 of its 140 references that are in the map. - First posted on arXiv 25 Dec 2025. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 12 of 12) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024) - [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025) - [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025) - [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025) - [Translation between Molecules and Natural Language](https://mlsanity.com/paper/2204.11817/) (2022) - [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025) - [Evaluating Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2512.15567/) (2025) - [Nature Language Model: Deciphering the Language of Nature for Scientific Discovery](https://mlsanity.com/paper/2502.07527/) (2025) - [ToolUniverse: An open platform for democratizing AI scientists](https://mlsanity.com/paper/2509.23426/) (2025) - [textttMiniMol: A Parameter-Efficient Foundation Model for Molecular Learning](https://mlsanity.com/paper/2404.14986/) (2024) - [Multi-agent systems for chemical engineering: A review and perspective](https://mlsanity.com/paper/2508.07880/) (2025) - [Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL](https://mlsanity.com/paper/2505.20578/) (2025) ## Built on by (most cited first, 19 of 19) - [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025) - [Benchmarking AI Agents for Addressing Scientific Challenges Across Scales](https://mlsanity.com/paper/2606.12736/) (2026) - [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026) - [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026) - [Purely Agent-Driven Black-Box Optimization for Biological Design](https://mlsanity.com/paper/2601.22382/) (2026) - [Towards Diverse Scientific Hypothesis Search with Large Language Models](https://mlsanity.com/paper/2606.10587/) (2026) - [A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization](https://mlsanity.com/paper/2605.06226/) (2026) - [Open-Ended Task Discovery via Bayesian Optimization](https://mlsanity.com/paper/2605.07572/) (2026) - [Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science](https://mlsanity.com/paper/2603.28361/) (2026) - [On the Creativity of AI Agents](https://mlsanity.com/paper/2604.13242/) (2026) - [Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution](https://mlsanity.com/paper/2604.16322/) (2026) - [DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery](https://mlsanity.com/paper/2605.15461/) (2026) - [StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery](https://mlsanity.com/paper/2606.11851/) (2026) - [Scientific discovery as meta-optimization: a combinatorial optimization case study](https://mlsanity.com/paper/2606.26728/) (2026) - [Recipes for Steering and Scaling LLMs via Sampling](https://mlsanity.com/paper/2608.26120/) (2026) - [INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery](https://mlsanity.com/paper/2602.01815/) (2026) - [Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications](https://mlsanity.com/paper/2609.07254/) (2026) - [RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis](https://mlsanity.com/paper/2609.35549/) (2026) - [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026) ## Abstract (arXiv) There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.