LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
cs.AI, cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/QwenLM/Qwen3.8
Terminology
Sources
- DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
- Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning
- Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
- Formal Policy Enforcement for Agentic Systems
- Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving
- Agent Safety Alignment via Reinforcement Learning
- Progent: Securing AI Agents with Privilege Control
- Beyond Solver Verdicts: Generative Reward Models for Autoformalization
- Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
- Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents