Posts
All the articles I've posted.
-
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Published: at 11:12 AM
76.49 🤔ARTIST, a novel framework unifying agentic reasoning, reinforcement learning, and tool integration, enables LLMs to autonomously orchestrate external tools within multi-turn reasoning, achieving up to 22% accuracy gains on complex math tasks and significant improvements in multi-turn function calling over baselines.
-
TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-Experts
Published: at 12:11 AM 76.46 🤔本文提出TT-LoRA MoE框架，通过两阶段训练结合张量分解的低秩适配器和动态稀疏路由机制，以极低的参数量（LoRA的2%，AdapterFusion的0.03%）实现多任务NLP分类任务的竞争性性能，平均准确率提升约4个百分点，同时解决任务干扰和知识遗忘问题。
-
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
Published: at 12:12 AM 76.38 🤔本文提出了一种通过分割大型语言模型推理轨迹为子思维并从中间状态生成多条推理路径、最终以众数聚合答案的方法，显著提高了数学推理任务的准确性（最高提升13%），并揭示了答案一致性与正确性的相关性。
-
LLM-e Guess: Can LLMs Capabilities Advance Without Hardware Progress?
Published: at 11:20 AM 76.16 🤔This paper introduces a framework to classify algorithmic innovations in LLMs as compute-dependent or compute-independent, demonstrating through small-scale GPT-2 experiments that compute-independent advancements like FlashAttention can yield up to 3.5× compute-equivalent gains even under hardware constraints, challenging the efficacy of hardware-focused AI regulation.
-
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
Published: at 04:29 PM 76.05 🤔本文提出MINDcraft框架和MineCollab基准，评估LLM在多代理具身协作中的性能，揭示了当前模型在通信和协调方面的局限性，并呼吁开发更先进的协作方法。