9 papers
TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
Jiangping Huang, Wenguang Ye, Weisong Sun +3
Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/f…
LongCat-Flash-Thinking-2601 Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +162
We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thi…
Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making
Wentao Zhang, Qunbo Wang, BoXuan Zhao +7
Large language model (LLM) agents often rely on external demonstrations or retrieval-augmented planning, leading to brittleness, poor generalization, and high computational overhea…
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
Xinmeng Hou, Peiliang Gong, Bohao Qu +3
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-im…
SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents
Alejandro Cuadron, Pengfei Yu, Yang Liu +1
Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: \emph{do all act…
MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
Zimeng Huang, Jinxin Ke, Xiaoxuan Fan +9
Large Vision-Language Models (LVLMs) have exhibited remarkable progress. However, deficiencies remain compared to human intelligence, such as hallucination and shallow pattern matc…