…AI-generated summary The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of…
…achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents. View arXiv page View…
…Recent agentic-memory systems pursue the consolidated form: an LLM rewrites past trajectories into a textual memory bank that it continuously updates with new interactions, promising self-improving agents without parameter updates…
…Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement (2026) HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents (2026) Kintsugi: Learning Policies by Repairing Executable Knowledge Bases (2026…
…Compared with agent-driven wiki-walk memory, it reduces latency by 82.95 percent, token cost by 82.29 percent, and stale-knowledge usage by 96.58 percent, while improving quality by…
Papers arxiv:2606.23049 Training Open Models for Agentic Phone Use Published on Jun 22 Submitted by taesiri on Jun 23 Tencent Hunyuan Authors: Zhengyang Tang , , , Xinyuan Wang , , , , , , Junyi Li , , , , , , , , Sunqi Fan…
…Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization (2026) Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration (2026) Evaluating Temporal Consistency in Multi-Turn Language Models (2026…
…Through a closed-loop run--verify--reflect process , the framework jointly improves decomposition and execution over time via persistent, human-readable external memory , with self-evolving updates to each single-agent. During…
…Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback (2026) Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging (2026) SPADER: Step-wise Peer Advantage with Diversity-Aware…
…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…