arXiv AI

TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery

TRACE is a transition‑aware residual control framework designed to improve multi‑objective materials discovery with large language model agents. It records each local refinement as a parent‑edit‑child transition, aggregates evidence to estimate reusable edit effects, and ranks future edits by their predicted ability to reduce remaining constraint violations while protecting already satisfied objectives. In a controlled comparison, TRACE outperforms the state‑of‑the‑art LLEMA baseline, raising the macro‑average hit rate from 18.13% to 25.96%.

arXiv Computation and Language

4d ago

Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis

The paper introduces RIPPLE, a method for adapting workflow-synthesizing agents through prompt-policy editing without retraining the underlying model. RIPPLE diagnoses failed execution trajectories, maps failures to specific policy segments, and restricts edits to those segments. It then evaluates candidate edits in isolation and replays only those that remain safe after composition, achieving up to a 23.1% improvement in validation success on a synthetic benchmark and positive gains on additional language‑model backbones.

By Manqing Mao, Hong Wang, Samson Koelle, Jie Yuan, Zhuoer Wang, James Feng, Yanjun Lin, Daniel Edmiston, Nikki Lijing Kuang, Zhecheng Sheng, Wei Niu

agents benchmarks

arXiv AI

Jul 1

Contrastive Reflection for Iterative Prompt Optimization

arXiv:2606. 30840v1 Announce Type: new Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation.

By Derek Koh, Jinghui Mo, Benjamin H. Le, Jiening Zhan, Baofen Zheng, Kevin Bevis, Nathaniel C. Owen, Lauren Elizabeth Charney, Wenqiong Liu, Jingwei Wu

llms rag agents

arXiv AI

Sep 7

TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing

arXiv:2609. 05019v1 Announce Type: new Abstract: Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed.

By Tianxing Wang, Mingming Zhao, Shuai Huang, Huiyang Xu, Chaoyue Niu, Shengzhong Liu, Fan Wu

llms agents benchmarks

arXiv Machine Learning

Aug 4

Progressive Agent Skill Generation via Reinforcement Learning

arXiv:2608. 01678v1 Announce Type: new Abstract: Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence sources.

By Junhao Shen, Zhanqiu Zhang, Yiwen Guo, Hong Cheng

llms agents reinforcement-learning

arXiv AI

Jun 2

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

arXiv:2606. 01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures.

By Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, Yiyan Ji, Yauwai Yim, Hongyu Luo, Xiyu Ren, Ruan Chenyu, Haoran Li, Yangqiu Song

llms agents benchmarks

arXiv Machine Learning

Aug 3

Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination

arXiv:2607. 28947v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to solve complex problems by searching over program space, offering a general paradigm for scientific problems that can be naturally represented and solved as programs.

By Jingwen Fu, Zhen Liu, Yuhan Liu, He Zhang, Nanning Zheng

llms agents robotics

arXiv Machine Learning

Aug 4

CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization

arXiv:2606. 14581v4 Announce Type: replace Abstract: High-throughput experimentation can evaluate many reaction conditions, yet combinatorial condition spaces still exceed the available experiment budget.

By Guanyu Liu, Weiyi Kong, Chao Tang, Zeyu Wang, Boer Zhang, Baiqing Li, Peiyu Zhang, Tianyu Shi

llms efficiency

arXiv AI

Jun 15

SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing

arXiv:2606. 14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows.

By Haowen Gao, Haoran Chen, Can Wang, Shasha Guo, Liang Pang, Zhaoyang Liu, Huawei Shen, Xueqi Cheng

llms agents

arXiv AI

Aug 14

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback

arXiv:2608. 13120v1 Announce Type: new Abstract: Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause.

By Qianxi Yan, Chunrong Chen, Jiuzhou Zhao, Min Zhang, Yongzhou Xu, Xiaochuan Xu

llms agents

arXiv AI

Aug 10

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

arXiv:2608. 07196v1 Announce Type: new Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples.

By Chao Fei, Qingyi Si, Kaihua Liang, Yanghua Xiao, Panos Kalnis, Hongcheng Guo

llms agents benchmarks

arXiv AI

Jun 16

PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents

arXiv:2606. 16215v1 Announce Type: cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns.

By Zhenbang Du, Jun Luo, Zhiwei Zheng, Xiangchi Yuan, Kejing Xia, Dachuan Shi, Qirui Jin, Qijia He, Shaofeng Zou, Yingbin Liang, Wenke Lee

agents reinforcement-learning fine-tuning

arXiv AI

Jul 1

ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents

arXiv:2606. 31392v1 Announce Type: new Abstract: Tool-augmented vision-language models (VLMs) can solve multimodal, multi-step tasks by calling external tools, yet they remain fragile in practice.

By Binjie Zhang, Mike Zheng Shou

llms agents reinforcement-learning fine-tuning multimodal

Related stories