arXiv AI June 2, 2026 By Hongyi Cen, Mingxin Wang, Yule Liu, Jingyi Zheng, Hanze Jia, Tan Tang

AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification

arXiv:2604. 07967v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, weaken, or correct the false proposition they are supposed to preserve.

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

arXiv Machine Learning

Jul 30

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.

By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov

llms benchmarks

arXiv AI

Jul 15

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.

By Junyu Ren

llms agents safety

arXiv AI

Jul 29

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.

By Genliang Zhu (Accentrust, Georgia Institute of Technology), Chu Wang (Accentrust, University of Illinois Urbana-Champaign)

agents safety

arXiv AI

Jun 19

CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis

arXiv:2606. 19819v1 Announce Type: cross Abstract: Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking.

By Phuong Huu Vu Tran, Thuan Duc Mai, Bach Xuan Le

llms benchmarks

arXiv AI

Jun 2

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

arXiv:2606. 01441v1 Announce Type: new Abstract: Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations.

By Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong

llms agents safety

arXiv AI

Jul 8

Proof of Execution: Runtime Verification for Governed AI Agent Actions

arXiv:2607. 05397v1 Announce Type: cross Abstract: Agent systems increasingly execute rather than advise.

By James Rhodes, George Kang

agents

Related stories

ToxScreen: Detecting Whether an LLM Has Been Poisoned

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

Proof of Execution: Runtime Verification for Governed AI Agent Actions