Protecting Shared Agent Workflows from Invalidation Attacks with Signed Trajectories and Runtime Verification
cs.CR
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/DachengLi1/LongChat
Terminology
Sources
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- $A^2Flow:$ Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
- CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
- Get Experience from Practice: LLM Agents with Record & Replay
- G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- INMS: Memory Sharing for Large Language Model based Agents
- Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
- A-MEM: Agentic Memory for LLM Agents
- Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Towards Trustworthy Federated Learning with Untrusted Participants
- The Llama 3 Herd of Models
- Qwen2.5-VL Technical Report
- Qwen3 Technical Report
- Measuring Mathematical Problem Solving With the MATH Dataset
- Program Synthesis with Large Language Models
- TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
- CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks
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