arXiv AI July 14, 2026 By Kyoungmin Kim, Anastasia Ailamaki

Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]

arXiv:2607. 10508v1 Announce Type: cross Abstract: LLM agents that conduct research (proposing ideas, writing and running code, analyzing results) can already carry a study from research question to figures, yet cannot be fully trusted.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 13

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

arXiv:2602. 20064v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results.

By Zac Garby, Andrew D. Gordon, David Sands

llms agents benchmarks

arXiv AI

Jul 8

PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates

arXiv:2607. 05483v1 Announce Type: cross Abstract: Agentic workflows often operate over shared, structured state.

By Zhaoyu Bai, Jiaqi Cai

llms rag agents benchmarks

arXiv AI

Jul 15

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.

By Junjie Yin, Xinyu Feng

llms agents benchmarks

arXiv AI

Jun 6

TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory

arXiv:2606. 06240v1 Announce Type: cross Abstract: Persistent memory for an LLM agent is a write-heavy substrate: every belief update is a versioned write, and a new claim may contradict a stored one.

By Ziming Wang

llms agents

arXiv AI

Jun 24

LemonHarness Technical Report

arXiv:2606. 24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration.

By Kailong Ren, Fubo Sun, Jiachen Liu, Liu Yang, Zimo Yin, Jiaying Li, Congli Yin, Ming He, Yu Huo, Jiawei Liu, Zeping Chen, Yubin Huangfu, Ronghua Li, Yixuan Wu, Xing Su, Yanzhi Xu, Likang Wu, Hongke Zhao, Lei Zhang, Xiaohui Geng, Jianping Fan

llms rag agents

arXiv AI

Aug 5

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.

By Salma El Yadouni (EPFL), Guanyi Li (Binome Technologies)

llms agents benchmarks

Related stories

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory

LemonHarness Technical Report

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows