…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Multimodal large language models are increasingly deployed as long-horizon agents , where memory must do more than recall: it must track an evolving world…
…Persona benchmark evaluates agent performance on personalized tools interacting with individual accounts and local databases, revealing significant challenges in current SOTA agents. Generated by Qwen/Qwen2.5-Coder-32B-Instruct The Model…
…View arXiv page View PDF GitHub 4 Add to collection Community AgensFlow introduces an open-source coordination-policy substrate for multi-agent systems. Instead of hard-coding agent workflows upfront, the framework…
…LLM itself can reflectively patch stale prompts and code into useful evolution signal rather than discard them. Get this paper in your agent: hf papers read 2605.08520 Don't have the…
…Chenghao Zhang , , , , Abstract Multi-agent system for generating reliable, visually informative multimodal reports by interleaving textual and visual evidence through specialized agents and verification mechanisms. Generated by Qwen/Qwen2.5-Coder-32B…
…Evaluating 27 LVLMs and 7 memory-augmented agents , we find that long-context LVLMs achieve high short-context accuracy through direct visual grounding but degrade as conversations grow, whereas memory agents are…
…code at https://github.com/CherYou/ AutoResearchBench . View arXiv page View PDF Project page GitHub 39 Add to collection Community This paper introduces AutoResearchBench, a benchmark specifically designed to evaluate AI agents…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important. A minimal intervention is…
…Three Hypotheses on AI-Assisted Code Review (2026) Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents (2026) Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using…
…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…
