Search papers, labs, and topics across Lattice.
Renmin University of China
6
0
8
LLM agents are shockingly vulnerable to multi-stage "trojan" attacks that inject malicious instructions into their workspace, achieving near-perfect success rates where standard prompt injection defenses fail.
Scaling out peer agents with a shared reasoning hub, AgentFugue, unlocks a new dimension of capability gains in long-horizon tasks, proving that collective reasoning is more than just parallel compute.
Agent-World reveals that self-evolving environments can dramatically boost agent performance, outperforming established models by leveraging dynamic task synthesis.
Forget trajectory-level rollouts: MuSEAgent learns faster and reasons better by distilling past interactions into reusable, state-aware decision experiences.
Observational user feedback, often dismissed as too noisy and biased, can actually power effective RLHF with the right causal modeling, achieving a 49.2% gain on WildGuardMix.
Current multimodal models are stuck in bi-modal interactions, but OmniGAIA and OmniAtlas offer a path towards truly omni-modal AI assistants capable of reasoning and tool use across video, audio, and images.
