Auditing Provenance Sensitivity in LLM Agent Action Selection
cs.AI
Submitted: 2026-07-23
Updated: 2026-11-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- ACEBench: Who Wins the Match Point in Tool Usage?
- Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
- Defeating Prompt Injections by Design
- WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
- AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
- CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
- System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- ReAct: Synergizing Reasoning and Acting in Language Models
- ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
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