Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning

arXiv:2609.29697 · cs.CR, cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/langchain-ai/langchain

Terminology

• Calibration — 48× in this paper · explained in 7 episodes
• Trace — 15× in this paper · explained in 2 episodes
• Verification — 12× in this paper · explained in 2 episodes
• Agent Architectures — 8× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Attack Success Rate — 5× in this paper
• Benchmarking — 4× in this paper · explained in 3 episodes
• Direct Prompt Injection — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Perplexity — 3× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cooperation — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
• Detecting Language Model Attacks with Perplexity
• Thought Anchors: Which LLM Reasoning Steps Matter?
• Defeating Prompt Injections by Design
• WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
• PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification
• Understanding the planning of LLM agents: A survey
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• AgentBench: Evaluating LLMs as Agents
• Ignore Previous Prompt: Attack Techniques For Language Models
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
• From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
• Cognitive Overload Attack:Prompt Injection for Long Context
• ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
• ReAct: Synergizing Reasoning and Acting in Language Models
• GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
• UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
• Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
• MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs