Related papers: Dr. Zero: Self-Evolving Search Agents without Trai…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

AI self-evolution has long been envisioned as a path toward superintelligence, where models autonomously acquire, refine, and internalize knowledge from their own learning experiences. Yet in practice, unguided self-evolving systems often…

In the quest for super-human performance, Large Language Models (LLMs) have traditionally been tethered to human-annotated datasets and predefined training objectives-a process that is both labor-intensive and inherently limited. This paper…

Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps,…

Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks. However, designing effective evolving methods for instruction evolution requires substantial human expertise.…

Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on…

DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critically examine R1-Zero-like training by analyzing its two core…

Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and high-quality human feedback. However, as base LLM models…

Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances in reasoning-oriented (``thinking'') models. Such…

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher models or reliable…

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple models. While multi-agent frameworks can…

Traditional task-oriented dialog systems are unable to evolve from ongoing interactions or adapt to new domains after deployment, that is a critical limitation in real-world dynamic environments. Continual learning approaches depend on…

Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software…

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through…

Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the…

Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce…