OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
arXiv preprint arXiv:2504.06821 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
SkillTrojan demonstrates that backdoors can be placed in composable skills of agent systems to achieve up to 97% attack success rate with only minor loss in clean-task accuracy.
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
SkillSafetyBench shows that localized non-user attacks via skills and artifacts can consistently induce unsafe agent behavior across domains and model backends, independent of user intent.
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.
citing papers explorer
-
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
-
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
SkillTrojan demonstrates that backdoors can be placed in composable skills of agent systems to achieve up to 97% attack success rate with only minor loss in clean-task accuracy.
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
SkillSafetyBench shows that localized non-user attacks via skills and artifacts can consistently induce unsafe agent behavior across domains and model backends, independent of user intent.
-
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.