arXiv Computation and Language

Can Large Language Models Forecast What Researchers Study Next?

arXiv Machine Learning
Oct 3

Do Your Own Research: Learning to Forecast by Learning to Search

The paper introduces an agentic forecasting environment built on 2,100+ resolved Polymarket questions, where a language model (Qwen3.5-35B-A3B) learns to gather evidence during rollout via web search, page reading, and financial time series, all filtered to avoid post‑cutoff leaks. Training with single‑epoch GRPO and a Brier‑score reward improves calibration by 30‑40% and reduces search attempts, while the trained policy outperforms four frontier models in evidence‑based forecasting, achieving lower soft‑Brier scores at roughly 5% of the inference cost. The authors release the environment, dataset, and per‑rollout records as a reusable harness for temporal forecasting agents.

By Yusuf Afifi, Artur Kiulian, Anton Polishko, Mykola Khandoga, Hamudi Naanaa, Alina Krasnobrizha
arXiv Computation and Language
Sep 30

Can Language Models Learn to Forecast Stock Prices

arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,...

By Jiacheng Guo, Suozhi Huang, Shuzhen Li, Yunlong Gao, Zerui Cheng, Jason Ge, Shushu Liang, Zihao Li, Hao Lu, Ming Yin, Shilong Liu, Jiashuo Liu, Xu Kuang, Mengdi Wang
arXiv Computation and Language
Nov 4

RAP: Research Attention Prediction in Language Agents

The paper introduces Research Attention Prediction (RAP), a benchmark designed to evaluate large language model (LLM) agents’ ability to infer changes across entire research fields from limited evidence gathered during online scholarly searches. RAP is built on a local search environment comprising 356,357 dated arXiv papers and includes two evaluation sets: a Core set of 2,160 questions covering 54 AI/ML fields and an Extended set spanning 269 fields. Experiments show that while search improves agents’ recognition of recent changes, their forecasting of future shifts remains limited or even negative, indicating that LLM agents can detect some recent developments but struggle to reliably anticipate future research activity.

By Yingqian Wu, Jingcong Liang, Shengbin Yue, Siyuan Wang, Zhenfei Yin, Junchi Yu, Zhongyu Wei
arXiv Computation and Language
Nov 4

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

IdeaTaste is a benchmark that evaluates large language models (LLMs) on their ability to generate research proposals that align with what human researchers actually publish. The study compares proposals generated by six contemporary LLMs against real papers from four research areas, finding that LLMs achieve only about 26% of the citation matching and 18% of the idea matching of human communities. Even larger LLM populations and richer field contexts do not close this gap, indicating that LLMs struggle more with translating research directions into concrete approaches than with selecting the right topics.

By Shanshan Zhong, Chen Xu, Jingjie Ning, Zhengzhong Liu, Aviral Kumar, Chenyan Xiong
arXiv AI
Jun 9

GIScholarBench: Benchmarking LLM Overconfidence in GIS Research

arXiv:2606. 08036v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore expose a key weakness: overconfidence.

By Zongrng Li, Mingzheng Yang, Lei Zou, Hongxu Ma, Hao Tian, Siqi Zhou, Wenjing Gong, Kaili Zhang, Bingqian Chen, Mitch Zhang, Yifan Yang
arXiv AI
Jul 10

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

arXiv:2607. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.

By Rapha\"el Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana, Christopher J. Earls, Srikar Varadaraj, Eric Ho
arXiv AI
Oct 31

Hedge-Bench: Can Agents Reason Their Way to Better Predictions?

Hedge-Bench is a benchmark comprising 92 real-world environments derived from hedge fund analysts' reasoning traces, designed to test AI agents’ ability to forecast future events from incomplete information. Agents are evaluated on joint success—correct forecasts with over 60% research coverage—across 11 frontier models, achieving rates between 2.54% and 31.52%. Training Muse‑Glimmer with GRPO on 165 environments improves coverage on held‑out tasks and demonstrates generalization to out‑of‑distribution evaluations.

By Mahesh Ramesh, Eric Cho, Alice Lu, Shawn Huang, Baiqing Lyu