AI Paper Daily · Beijing Time

AI 论文日报 2026-07-07

覆盖北京时间日期:2026-07-06 与 2026-07-07

candidate count
795
new included count
390
selected count
12

Top 3

  1. EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer — 直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;对 coding agent 工程有启发。
  2. AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments — 直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;提供可复用评测视角。
  3. Hierarchical Evidence-Driven Reasoning for Long Document Understanding — 直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;可迁移到 RAG/知识工作流。
#1

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao, Zhao Wang · 2026-07-06 · arXiv:cs.AI

Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and ve…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;对 coding agent 工程有启发。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 4/5 · Evidence 3/5 · Actionability 3/5 · Total 23

PDF

#2

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo · 2026-07-06 · arXiv:cs.AI

Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic eval…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;提供可复用评测视角。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 3/5 · Actionability 4/5 · Total 23

PDF

#3

Hierarchical Evidence-Driven Reasoning for Long Document Understanding

Junyu Xiong, Yonghui Wang, Rongjian Gu, Chenyu Liu, Bing Yin · 2026-07-06 · arXiv:cs.AI

Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existi…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;可迁移到 RAG/知识工作流。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 3/5 · Actionability 4/5 · Total 23

PDF

#4

OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement

Adriana Laurindo Monteiro, Nayse Fagundes, Gabriel Mattos Langeloh, Gustavo de Oliveira Kanno, Priscila Louise Aguirre · 2026-07-07 · arXiv:cs.AI

We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulatio…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;对 coding agent 工程有启发。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 4/5 · Novelty 5/5 · Substance 4/5 · Evidence 3/5 · Actionability 3/5 · Total 22

PDF

#5

Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models

MY Pitsane, Hope Mogale · 2026-07-06 · arXiv:cs.AI

Large language models (LLMs) generate fluent outputs that can be wrong. Unlike humans, who often exhibit cues when providing false information, LLMs produce errors that are difficu…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;对 coding agent 工程有启发。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 2/5 · Actionability 4/5 · Total 22

PDF

#6

ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI

ACE-Brain Team, :, Ziyang Gong, Haoming Gu, Zehang Luo · 2026-07-06 · arXiv:cs.RO

Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, act through robot bodies, monitor progress, and improve f…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;可迁移到 RAG/知识工作流。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 2/5 · Actionability 4/5 · Total 22

PDF

#7

Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action Reasoning

Jiaxing Qi, Zhongzhi Luan, Hongyu Zhang, Shaohan Huang, Carol Fung · 2026-07-06 · arXiv:cs.SE

Large language models (LLMs) are increasingly used to interpret operational evidence and assist incident response in cloud-native microservice systems. However, recovery-oriented u…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;可迁移到 RAG/知识工作流。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 4/5 · Novelty 4/5 · Substance 4/5 · Evidence 3/5 · Actionability 4/5 · Total 22

PDF

#8

LLM-as-a-Verifier: A General-Purpose Verification Framework

Jacky Kwok, Shulu Li, Pranav Atreya, Yuejiang Liu, Yixing Jiang · 2026-07-07 · arXiv:cs.AI

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the abi…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;对 coding agent 工程有启发。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 3/5 · Actionability 2/5 · Total 21

PDF

#9

When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents

Yechao Zhang, Shiqian Zhao, Jiawen Zhang, Jie Zhang, Gelei Deng · 2026-07-06 · arXiv:cs.AI

Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. Thi…

为什么重要:直接触及 agent 系统/评测/协作能力;对 coding agent 工程有启发;提供可复用评测视角。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 5/5 · Substance 3/5 · Evidence 2/5 · Actionability 3/5 · Total 21

PDF

#10

Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems

Xinyu Lin, Yashar Deldjoo, Sunhao Dai, Honghui Bao, Xiaopeng Ye · 2026-07-06 · arXiv:cs.CL

The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive system…

为什么重要:直接触及 agent 系统/评测/协作能力;有助于推理与规划链路设计;提供可复用评测视角。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 5/5 · Novelty 4/5 · Substance 4/5 · Evidence 2/5 · Actionability 3/5 · Total 21

PDF

#11

RoboVista: Evaluating Vision Language Models for Diverse Robot Applications

Shuangyu Xie, Kaiyuan Chen, Ziyang Chen, Simeon Adebola, Yixuan Huang · 2026-07-06 · arXiv:cs.RO

Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision-…

为什么重要:有助于推理与规划链路设计;提供可复用评测视角。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 4/5 · Novelty 5/5 · Substance 3/5 · Evidence 4/5 · Actionability 2/5 · Total 21

PDF

#12

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Haozhe Wang, Weijia Feng, Jinpeng Yu, Che Liu, Ping Nie · 2026-07-07 · arXiv:cs.AI

Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending …

为什么重要:直接触及 agent 系统/评测/协作能力;提供可复用评测视角。

Lucian 下一步:检查 PDF 的 benchmark / ablation,并判断能否转化为 agent、RAG、coding 或 evaluation 原型。

Relevance 4/5 · Novelty 5/5 · Substance 3/5 · Evidence 2/5 · Actionability 3/5 · Total 20

PDF

数据源失败或不确定性说明

Scoring dimensions: Relevance · Novelty · Substance · Evidence · Actionability.

Markdown archive · All AI paper daily reports