…Finally, empirical results demonstrate improved long-horizon reasoning accuracy and a favorable accuracy-efficiency trade-off compared to state-of-the-art agentic memory systems. Our code is available at https://github…
…In the report, we summarize improvements in model design, multimodal training, reinforcement learning, toolchain expansion, and agent-framework integration, together with practical insights on building multimodal agents. GLM-5V-Turbo achieves strong…
…We further introduce ICU -Evo to study structured-memory agents that improves long-horizon reasoning but does not fully eliminate safety failures. Together, Real ICU provides a clinically grounded testbed for measuring…
…of open-ended coding problems from closed-ended tasks, improving LLM coding performance on benchmarks through diverse problem variants and enhanced agent interactions. AI-generated summary Many real-world coding challenges are…
…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…
…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…
…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…