…Minbeom Kim , , , , , , , , Abstract LiSA enables adaptive safety guardrails for AI agents by converting occasional failures into reusable policy abstractions and using evidence-aware confidence gating to improve performance under sparse and noisy…
…specific profiles significantly improving performance. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Personalization is a crucial capability of modern language agents . However, current research primarily positions personalized agents as passive responders…
…Software engineering agents are evaluated using a process-level framework that reveals differences between effective and ineffective approaches, identifying patterns like lucky passes and providing quality scoring for improved assessment. AI-generated…
…Continual learning expects an agent to accumulate reusable experience across a stream of tasks, improve over time, and avoid interference from irrelevant experiences. Unfortunately, existing benchmarks struggle to evaluate continual learning in…
…The following papers were recommended by the Semantic Scholar API AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations (2026) HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM…
…Despite the strong performance gains, coding agent based methods have high latency costs. While AgentRunbook-C advances the accuracy-latency Pareto frontier, substantial room for improvement remains. Together, these results establish LME…
…Rather than improving planner accuracy, Agent libOS demonstrates a runtime substrate in which long-running LLM agents can be scheduled, authorized, resumed, and audited without treating tool dispatch as the trust boundary…
…refines context-specific skills for language models through a multi-agent self-play loop with Challenger, Reasoner, and Judge components, improving context learning performance without human supervision. AI-generated summary Many real…
Papers arxiv:2606.03965 Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning Published on Jun 2 Submitted by Yu Xia on Jun 4 University of California at San Diego…
…AI-generated summary Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style…