…AI-generated summary As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete…
…Amir Saeidi , , , , , , Abstract Failure-Aware Meta-Agentic framework improves open-source LLM performance in conversational scenarios by identifying common errors and deploying specialized agents to correct them. AI-generated summary Large Language…
…Memory-as-Embedding Routing for Long-Term Conversational Agents (2026) MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents (2026) EviMem: Evidence-Gap-Driven Iterative Retrieval for…
…AI-generated summary Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and memory-augmented agents . However…
…The following papers were recommended by the Semantic Scholar API Skill Retrieval Augmentation for Agentic AI (2026) SkillX: Automatically Constructing Skill Knowledge Bases for Agents (2026) SkillLearnBench: Benchmarking Continual Learning Methods for…
…A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration (2026) AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science (2026) OrchMAS: Orchestrated Reasoning with Multi…
…The following papers were recommended by the Semantic Scholar API Co-Director: Agentic Generative Video Storytelling (2026) Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis (2026) DCARL…
…AI-generated summary Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start…
…A Live Agent Benchmark for Evolving Real-World Workflows (2026) Beyond Binary Correctness: Scaling Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks (2026) AcademiClaw: When Students Set Challenges for AI Agents…
…Wenbo Pan , , , , , , , Abstract Retrospective Harness Optimization (RHO) is a self-supervised method that improves AI agent performance by optimizing agent harness using only past trajectories through diverse task selection, parallel re-solving…