FGSS-BO introduces a Feedback‑Guided Search State (FGSS) framework that structures hypothesis management for large language model (LLM)‑guided Bayesian optimization. The system couples an LLM reflector, which proposes and revises hypotheses, with a deterministic curator that validates them and tracks test records, thereby linking language‑based guidance to observable evidence and parameter interventions. Applied to the LLAMBO platform, FGSS‑BO improves sample‑mean final best and search AUC on two retrospective protocol/media tasks, while also enabling inspection of hypotheses and their revisions across search rounds.
By Hao Chen, Ziyang Ling, Ronald X. Xu, Mingzhai Sun
The paper introduces LM2LM, a method that trains large language models (LLMs) to propose improvements for other LLMs using reinforcement learning (RL). It employs a frozen research world model (RWM) to predict the gains of proposals, providing a cheaper surrogate reward, and periodically validates high‑scoring proposals to keep feedback reliable. Experiments across eight LM development environments show that LM2LM enables a Qwen3.8‑27B model to outperform GPT‑6‑sol on held‑out tasks while reducing data‑generation cost by 33%, and it generalizes to unseen model families.
By Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He, Zhan Shi, Benoit Dumoulin, Xiang Zhang, Suhang Wang, Hanqing Lu
arXiv:2604. 00830v3 Announce Type: replace-cross Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time.
By Zhanzhi Lou, Hui Chen, Yibo Li, Qian Wang, Bryan Hooi
arXiv:2610.18572v1 Announce Type: new
Abstract: Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructi...
By Ruohong Liu, Bohan Tang, Lekang Jiang, Jack Umenberger, Yiwen Guo
OptiCom introduces a unified framework for state-conditioned composition in large language model (LLM)-driven optimization. It models LLM optimizers within a shared configuration space (artifact, query, operator, evaluation, memory, strategy) and uses an Optimization Controller to dynamically compose mechanisms while a Strategy Adapter refines long-term preferences. Experiments on 32 benchmark groups show OptiCom outperforms 14 configurations, achieving the top score in 23 groups.
By Chenxing Wei, Sichen Liu, Lizhao Liu, Ningyuan Sun, Chen Bingzhou, Ying He, Bo Jiang, Fei Yu, Yao Shu
arXiv:2606. 24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason.
By Tianyuan Shi, Canbin Huang, Bei Li, Xin Chen, Xiaojun Quan, Jingang Wang, Qifan Wang
arXiv:2606. 11206v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization.
By Yucheng Zhou, Junwei Sheng, Qianning Wang, Jianbing Shen
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
By Shuang Sun, Guoxin Chen, Fanzhe Meng, Jia Deng, Huatong Song, Jinhao Jiang, Wayne Xin Zhao, Hongteng Xu, Ji-Rong Wen
The paper introduces Feedback‑Enriched Environments (FEEs) as a new approach to training large language models as autonomous agents for long‑horizon tasks. By shifting from action guidance to observation enrichment during later stages of exploration, FEEs improve performance across SciWorld and BFCL benchmarks with various Qwen3 model scales and RL algorithms. The study shows that FEEs stabilize training, promote proactive exploration, embed environmental guidance into policy weights, and highlight intra‑group feedback consistency as key for stable optimization.
By Hongbang Yuan, Zhuoran Jin, Yixin Cao
The paper introduces Drift-Constrained Optimization (DCO), a framework that treats behavioral drift during fine‑tuning of instruction models as a bounded constraint rather than an uncontrolled side effect. By defining a drift budget, the authors reformulate fine‑tuning as a direction‑selection problem, showing that choosing different update directions can qualitatively change outcomes. Experiments on Qwen3 models demonstrate that carefully selected directions improve scientific reasoning and multilingual translation while preserving reasoning capabilities and general performance.
By Fei Yuan, Changjiang Gao, Yilei Tu, Yifeng Liu, Shujian Huang, Yu Qiao
The study demonstrates that providing scientific performance feedback to generative models can shift their search distribution toward productive regions that lie outside conventional training data. In reactor lattice design and chemical reaction-condition selection, this adaptation improves performance and increases the generation of previously excluded choices. The results also show that the identified productive regions can be reused to enhance random search and that removing target penalties alters the direction of adaptation toward the scientific objective.
By Yoon Pyo Lee, Samrendra Roy, Souvik Chakraborty, Syed Bahauddin Alam
arXiv:2608.23475v1 Announce Type: new
Abstract: As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm...
By Jinghan Tan, Yuanzheng Wang, Lu Chen, Zijun Chen, Yuqian Wang, Maosong Sun