Related papers: SAGE: Multi-Agent Self-Evolution for LLM Reasoning
Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…
The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus…
Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…
In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks…
Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…
Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…
Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…
Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through…
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…
Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often plateau quickly. A central failure mode is that the loop…
Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward…
Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…
Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like…
The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent \textit{reward bottleneck}: traditional reinforcement learning (RL) relies on scalar rewards that are \textbf{costly} to scale,…
Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action…
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement, for example, by reconstructing datasets with refined…
Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such…
Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external…