← Back to all news
arXiv AI By Ha Minh Hieu, Tongyao Zhu, Do Xuan Long, Min-Yen Kan

SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery

Read the original on arXiv AI →

SpecEvo is a multi‑Large Language Model framework that uses lightweight models to generate and refine candidate programs while an Advisor consolidates evidence from successes and failures. At sparse checkpoints, a frontier‑model Navigator intervenes with synthesis or refinement to address search stagnation. Across 176 tasks in scientific and algorithmic domains, SpecEvo matches or surpasses frontier‑model baselines, cuts API cost by up to 80%, and improves evaluation efficiency and benchmark performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 15

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output

The paper introduces SciSense, a framework that structures scientific ideation into eight cognitive stages and a dataset, SciSense-Traj, of 120K citation-conditioned research trajectories in both hindsight and foresight modes. It presents SciSense-LM, a family of LLMs trained on these trajectories, showing that hindsight-trained models yield higher-quality, more novel outputs and improve downstream coding agents’ research artifacts. The study demonstrates that outcome-anchored ideation reduces cognitive load for downstream agents, enabling more creative exploration.

By James Mooney, Zae Myung Kim, Young-Jun Lee, Dongyeop Kang
llmsagents
More like this →
arXiv AI
Jun 10

Towards Diverse Scientific Hypothesis Search with Large Language Models

arXiv:2606. 10587v1 Announce Type: cross Abstract: Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses.

By Haorui Wang, Parshin Shojaee, Kazem Meidani, Kunyang Sun, Jos\'e Miguel Hern\'andez-Lobato, Teresa Head-Gordon, Jiajun He, Chandan K. Reddy, Chao Zhang, Yuanqi Du
llms
More like this →
arXiv AI
Aug 17

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

arXiv:2608. 14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources.

By Mingming Zhao, Jiqian Dong, Kangping Xu, Zadid Hasan, Chengrui Fan, Shan Jiang, Shuai Mao, Ting Lingya, Linyi Zou, Tailin Zhou, Yun Hin Chan, Wenkai Zhang, Zhanhong Zhou, Guowei Huang, Hongliang Li, Wenjing Cun, Zhitang Chen, Mingxuan Yuan, Yanhui Geng
llmsagentsbenchmarks
More like this →
arXiv Machine Learning
Sep 14

PACEvolve: Enabling Progress-Aware Consistent Evolution

The paper introduces PACEvolve, a framework that improves self‑evolving agents powered by Large Language Models by addressing their tendency to become trapped in local contexts and repeat flawed hypotheses. It does so through three techniques: Hierarchical Context Management to prune memory, Momentum‑Based Backtracking to escape local minima, and a self‑adaptive Collaborative Evolution policy to balance refinement and knowledge transfer. These methods enable the agents to maintain a global view of search momentum and achieve state‑of‑the‑art results on complex evolutionary benchmarks.

By Minghao Yan, Bo Peng, Benjamin Coleman, Ziqi Chen, Zhouhang Xie, Shuo Chen, Zhankui He, Noveen Sachdeva, Isabella Ye, Weili Wang, Chi Wang, Ed H. Chi, Fernando Pereira, Wang-Cheng Kang, Derek Zhiyuan Cheng, Beidou Wang
llmsagentsefficiencybenchmarks
More like this →