# Learning to Predict Future-Aligned Research Proposals with Language Models

arXiv: https://arxiv.org/abs/2603.27146 · HTML: https://mlsanity.com/paper/2603.27146/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation](https://mlsanity.com/paper/2503.22708/) (2025)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [PaperRobot: Incremental Draft Generation of Scientific Ideas](https://mlsanity.com/paper/1905.07870/) (2019)
- [ResearchTown: Simulator of Human Research Community](https://mlsanity.com/paper/2412.17767/) (2024)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [Can Large Language Models Unlock Novel Scientific Research Ideas?](https://mlsanity.com/paper/2409.06185/) (2024)
- [IdeaBench: Benchmarking Large Language Models for Research Idea Generation](https://mlsanity.com/paper/2411.02429/) (2024)
- [Forecasting high-impact research topics via machine learning on evolving knowledge graphs](https://mlsanity.com/paper/2402.08640/) (2024)
- [Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper](https://mlsanity.com/paper/2511.04583/) (2025)
- [TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents](https://mlsanity.com/paper/2510.06579/) (2025)
- [Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives](https://mlsanity.com/paper/2601.20833/) (2026)
- [Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration](https://mlsanity.com/paper/2508.04575/) (2025)
- [Sci-Reasoning: A Dataset Decoding AI Innovation Patterns](https://mlsanity.com/paper/2601.04577/) (2026)
- [FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article](https://mlsanity.com/paper/2503.16561/) (2025)

## Built on by (most cited first, 8 of 8)

- [COMPOSE: Composing Future Theorems from Citations and Formal Structure](https://mlsanity.com/paper/2605.30333/) (2026)
- [ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment](https://mlsanity.com/paper/2606.00644/) (2026)
- [ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes](https://mlsanity.com/paper/2607.04439/) (2026)
- [RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases](https://mlsanity.com/paper/2609.10092/) (2026)
- [Learning to Ideate for Scientific Impact](https://mlsanity.com/paper/2609.29802/) (2026)
- [Inspire: Benchmarking Scientific Literature Search for Open Research Problems](https://mlsanity.com/paper/2609.33233/) (2026)
- [Priced Guidance: Can Language Models Generate Future Research Ideas?](https://mlsanity.com/paper/2610.04976/) (2026)
- [Learning Scientific Exploration from Human Research Decision Trajectories](https://mlsanity.com/paper/2610.07184/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published after the time. We operationalize this objective with the Future Alignment Score (FAS), computed via retrieval and LLM-based semantic scoring against a held-out future corpus. To train models, we build a time-consistent dataset of 21,835 paper occurrences across 3,642 instances from targets and their pre-cutoff citations, and synthesize reasoning traces that teach gap identification and inspiration borrowing. Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method. Our code and data are publicly available at https://github.com/Arthur-Heng/future-aligned-proposals.