LLM Guardrails

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 36% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 138

All topics

A Deterministic Control Plane for LLM Coding Agents
Jun 25, 2026Padmaraj MadathaAI Coding Agents LLM Guardrails
HappiestJuneMinds2026 Technologies (AIP Centre of Excellence)
Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation
Jun 25, 2026Dongbin NaLLM Guardrails CoT Reasoning
POSTECH
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
Jun 24, 2026Congbo Ma, Hu Wang, Yichun Zhang +1LLM Guardrails LLM Safety
New York University Abu Dhabi · Khalifa University · New York University
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Jun 23, 2026Pingchuan Ma, Zhaoyu Wang, Zimo Ji +5LLM Guardrails Program Synthesis
Zhejiang University of Technology · HKUST
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Jun 22, 2026SingGuard TeamLanguage Model Safety Evaluation LLM Guardrails
1AI Security Lab, Ant Group
IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages
Jun 22, 2026Parth Bramhecha, Smit Deshmukh, Sairaj Bodhale +2Multilingual Language Models Language Model Safety Evaluation
L3Cube-Labs, Pune
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Jun 20, 2026Jiayi Li, Kun ZhanLLM Guardrails Multimodal Large Language Models
Lanzhou University
A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
Jun 17, 2026Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman +1LLM Guardrails Indirect Prompt Injection
Sparkverse AI Ltd, Bradford, 100190, West Yorkshire, England, UK
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Jun 13, 2026Wenbo Yu, Bohua Wang, Hao Fang +10LLM Safety Benchmarks Language Model Safety Evaluation
Tsinghua University · Beijing Normal University · South China University of Technology +2
OSGuard: A Benchmark for Safety in Computer-Use Agents
Jun 13, 2026Mina Mohammadmirzaei, Jeffrey FlaniganComputer-Use Agents LLM Guardrails
University of California, Santa Cruz
Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis
Jun 12, 2026Andoni Rodríguez, Alberto Pozanco, Daniel BorrajoLLM Guardrails Deception in Language Models
J.P. Morgan AI Research
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
Jun 12, 2026Yuguang Zhou, Xunguang Wang, Pingchuan Ma +3LLM Guardrails Adversarial Attacks on LLMs
1The Hong Kong University of Science and Technology · 2Zhejiang University of Technology
BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
Jun 12, 2026Leonhard Waibl, Felix Michalak, Hadrien MariacciaLLM Safety Benchmarks LLM Guardrails
University of Graz, Graz, Austria · Supervised Program for Alignment Research (SPAR) · Centre pour la Sécurité de l’IA (CeSIA), Paris, France.
A Safety-First Gateway Architecture for Trusted Public Health Resource Navigation
Jun 11, 2026Ben Torkian, Jun ZhouLLM Guardrails LLM Safety
University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA
Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance
Jun 11, 2026Ben Torsion, Jun ZhouMulti-Agent LLM Systems LLM Guardrails
University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA
FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization
Jun 11, 2026Jianwei Wang, Guoyang Shen, Yanhong Wu +5LLM Guardrails Over-Refusal
South China University of Technology · BUAA
Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM System
Jun 10, 2026Alyssa Unell, Miguel Fuentes, Brenna Li +4LLM Guardrails Clinical Language Model Evaluation
Department of Computer Science Stanford University Stanford, CA 95305 · Department of Medicine Stanford University Stanford, CA 95305 · Department of Biomedical Data Science Stanford University Stanford, CA 95305
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
Jun 9, 2026Huizhen Shu, Xuying Li, Piao XueLLM Guardrails Safety Filtering
ModelOneAI · yunshanai
Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human
Jun 8, 2026Emre TuranLearning to Defer LLM Guardrails
Independent Researcher
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails
Jun 4, 2026Marco Antonio Stranisci, A Pranav, Rossana Damiano +2LLM Guardrails Training Data Curation
University of Turin, Italy · Trustworthy AI Lab, University of Hamburg, Germany · IT University of Copenhagen, Denmark
From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
Jun 4, 2026Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3LLM Guardrails LLM Agent Training
1The University of Melbourne · 2Tsinghua University · †Corresponding author.
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
Jun 4, 2026Minseok Choi, Seungbin Yang, Dongjin Kim +5LLM Guardrails Safety Filtering
♡KAIST AI · ♣Financial Tech Lab, KakaoBank Corp
GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection
Jun 4, 2026Paulo Ricardo Ferreira Neves, Edson Rodrigues da Cruz Filho, Paulo Henrique Eleuterio Falsetti +7LLM Guardrails Neural Network Robustness
Quickium Technology Ltd. – Piracicaba, São Paulo · Federal Institute of Education, Science and Technology of São Paulo (IFSP) – Piracicaba Campus – São Paulo · Federal University of São Carlos (UFSCar) – Sorocaba Campus – São Paulo
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
Jun 2, 2026Qinyan Zhou, Peixin Zhang, Jun Sun +2LLM Guardrails LLM Refusal Behavior
Southeast University, China · School of Computing and Information Systems, Singapore Management University, Singapore · Zhejiang University, China +1
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jun 1, 2026Jiaqi Yu, Xin Wang, Yixu Wang +4Language Model Safety Evaluation LLM Guardrails
1Fudan University · 2Shanghai AI Laboratory
Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense
Jun 1, 2026Nataraj Agaram Sundar, Tejas MorabiaFinancial Services LLM Guardrails
eBay Inc. San Jose, CA, USA
Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case Study
May 31, 2026Nataraj Agaram Sundar, Tejas MorabiaLLM Guardrails Human-in-the-Loop Evaluation
eBay Inc. · San Jose, CA, USA
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
May 31, 2026Yunhao Feng, Xiaohu Du, Xinhao Deng +13LLM Guardrails AI Agent Safety
1Fudan University · Ant Group · 8ShanghaiUniversity +5
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
May 31, 2026Huanli Gong, Zhipeng Wei, Yu Fu +4LLM Guardrails Multi-Turn Jailbreak Attacks
University of California, Berkeley · International Computer Science Institute · University of California, Riverside +1
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
May 29, 2026Yan Wang, Zhixuan Chu, Zihao Xue +9LLM Guardrails LLM Safety Alignment
Alibaba Group · Zhejiang University · Huzhou Normal University +1

Jun 25, 2026, cs.SEJ/K move · Enter open · S save

A Deterministic Control Plane for LLM Coding Agents

Padmaraj Madatha

HappiestJuneMinds2026 Technologies (AIP Centre of Excellence)

AI Coding Agents LLM Guardrails LLM Agent Security AI Agent Governance Tool Access Control for LLM Agents

Open paper AskPDF arXiv

LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged. A prevalence study of 10,008 public GitHub repositories (n=6,145 agent config files) finds that agent configurations propagate as undeclared shared components: 10.1% of tracked paths are SHA-256 exact duplicates across independent repositories (fork-adjusted, threshold-independent), with 75.5% of clone pairs crossing organisational boundaries. Two further patterns are indicative: configurations are rarely revised (58% single-commit; 0.4 vs 0.6 commits/month age-normalised against CI/CD workflows), and rarely declare permission boundaries (<1% of agent configs vs 33% of Actions workflows, n=31 true positives). We propose a deterministic control plane above the harness that maps one-to-one to these gaps. Rel(AI)Build treats agent definitions as a managed supply chain (SHA-256 content addressing, HMAC-stamped lockfiles, hash-chained audit logs); enforces tiered permissions and attack-derived blocklists before LLM invocation; gates feature work through a phase state machine with requirement-to-file-to-test traceability; compiles a single canonical definition to seven IDE targets; and detects prompt drift via Jaccard similarity. Conformance tests on injected violations confirm each mechanism enforces its stated invariant; developer outcomes remain future work. Governance of this layer must be deterministic and tool-agnostic -- not delegated to further LLM orchestration.

Momentum

Related topics

Latest papers 138