View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $10K - $14K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (27)

[1]
Memory poisoning attacks on retrieval-augmented Large Language Model agents via deceptive semantic reasoning
2026Hao Jing, Fanxiao Li et al.
[2]
EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
2026Yufei He, Juncheng Liu et al.
[3]
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
2026Yibo Li, Zijie Lin et al.
[4]
MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
2025S. Srivastava, Haoyu He
[5]
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
2025Tianxin Wei, Noveen Sachdeva et al.
[6]
EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
2025Yufei He, Juncheng Liu et al.
[7]
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
2025Shuai Shao, Qihan Ren et al.
[8]
SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
2025Jiaye Lin, Yifu Guo et al.
[9]
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
2025Yufei He, Ruoyu Li et al.
[10]
AlphaEvolve: A coding agent for scientific and algorithmic discovery
2025Alexander Novikov, Ngân V˜u et al.
[11]
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
2025Chunyang Li, Junwei Zhang et al.
[12]
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
2025Zhiyuan Chang, Mingyang Li et al.
[13]
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
2025Yulin Chen, Haoran Li et al.
[14]
Can Indirect Prompt Injection Attacks Be Detected and Removed?
2025Yulin Chen, Haoran Li et al.
[15]
Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
2025Yufei He, Yuexin Li et al.
[16]
Defense Against Prompt Injection Attack by Leveraging Attack Techniques
2024Yulin Chen, Haoran Li et al.
[17]
Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
2024Cody Clop, Yannick Teglia
[18]
Self-evolving Agents with reflective and memory-augmented abilities
2024Xuechen Liang, Meiling Tao et al.
[19]
ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models
2024Jinheon Baek, S. Jauhar et al.
[20]
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
2024Wei Zou, Runpeng Geng et al.

Showing 20 of 27 references

Founder's Pitch

"Exploring persistent security risks in self-evolving LLM agents with potential covert memory exploits."

AI SecurityScore: 1View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

0/4 signals

0

Quick Build

0/4 signals

0

Series A Potential

1/4 signals

2.5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 2/17/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.