Filtered to large language models · clear filter
This paper introduces Kimi K3, a large-scale, open-source AI model that achieves state-of-the-art performance on a range of tasks, including vision and coding, and is designed to be more efficient and scalable than previous models, making it a promising candidate for real-world applications.
This paper introduces ZGCM-1, a highly efficient foundation model for math and agentic search that combines internal thinking with external tool use, and shows it can perform well on various benchmarks despite its compact size. Practitioners may care about the efficiency improvements and scalable architecture of ZGCM-1.
This paper proposes a method to determine which past update evidence in a large language model is still relevant and useful after subsequent training, to prevent wasting compute and potentially degrading the model's performance. Practitioners in the field of autonomous systems and language models might care about this problem because it can lead to better model performance and efficiency in adapting to changing domains and requirements.
This paper introduces RAGU, an open-source GraphRAG engine that improves large language models with structured knowledge by separating extraction and consolidation, and trains a compact extractor that outperforms larger models on knowledge-graph construction and GraphRAG tasks. Practitioners might care because RAGU can efficiently generate more accurate and complete context for tasks like factoid-level evidence recall and multi-hop question answering.
This paper proposes a new framework for training autonomous agents to perform multi-turn tool-calling tasks, addressing the challenge of dealing with vast solution spaces by using a diamond topology-aware approach. Practitioners may care about this research because it can help improve the performance of autonomous agents in complex tasks.
This paper reveals a vulnerability in how large language model providers store and return their models' step-by-step reasoning, allowing attackers to extract sensitive information and potentially inject malicious code. Practitioners should care because this vulnerability can be exploited to steal proprietary models' reasoning and private data, as well as inject malicious payloads into public models.
This paper evaluates how well large language model (LLM) agents can perform long-term tasks in a real-world e-commerce setting, where they need to make decisions over time and adapt to changing conditions. Practitioners in e-commerce and AI research can learn from this study to improve the performance of LLM agents in similar environments.
This paper investigates the role of training data in on-policy distillation, a technique used to improve large language models, and finds that even a single query can lead to significant improvements, but the process is slow and algorithm-starved.
This paper creates a database and search engine to help researchers and developers find and understand AI benchmarks, making it easier to evaluate and compare AI systems. Practitioners can use Benchmark Radar to discover and evaluate benchmarks, reducing the time and effort spent searching for relevant evaluations.
This paper introduces a new method to improve large language models (LLMs) called RLSVR, which uses a task-transformation technique to generate self-verifiable rewards, enabling LLM self-improvement on open-ended tasks. Practitioners might care about this because it could lead to more reliable and scalable self-improvement methods for LLMs.
This paper introduces a method called DecoEvo, which helps large language models improve by co-evolving a solver skill and a rubric-generator skill in a way that's more efficient and effective. Practitioners might care about this because it could lead to better performance and more reliable optimization in open-ended tasks.
This paper introduces a benchmark to measure how well large language models (LLMs) can prepare training data, and how well they evaluate the quality of that data. Practitioners might care because improving data preparation can lead to better model performance.