Search papers, labs, and topics across Lattice.
Affiliation:, Singapore Management University
5
0
8
7
The results show that the key to memory-augmented repair is not simply accumulating more experiences, but retrieving the right experiences for the right repair context, and that relevance, quality, and redundancy matter more than raw memory volume.
Existing debugging methods fail to reliably repair failures in multi-agent systems, with traditional approaches achieving less than 7% repair success.
Learning from user interactions, AgentAntibody evolves to effectively defend LLM agents against prompt injection, outperforming static defenses.
Existing defenses crumble when LLM agents face prompt injections that adapt to dynamic context, but ARGUS offers a robust solution by tracking the provenance of agent decisions.
GitHub abuse is more widespread and varied than previously thought, demanding a unified detection approach to safeguard software supply chains.
