The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

RAFT proposes a two-stage framework combining data refinement and adaptive distillation to improve domain-specific fine-tuning while mitigating the loss of general model capabilities.

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper introduces Andes, a framework that treats data generation as a plug-and-play agent skill, enabling autonomous alignment of LLMs by providing an intelligent, closed-loop data synthesis interf…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

The paper proposes EKSFT, a selective fine-tuning method that masks high-entropy or high-KL divergence tokens during Supervised Fine-Tuning (SFT) to prevent distribution shift and improve subsequent R…

The paper proposes projectional decoding, a novel framework that integrates a partial graph model alongside text generation to ensure the semantic validity of LLM-generated software artifacts.

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in spe…

This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.

The paper introduces State-Adaptive Prompt Optimization (SAPO), a novel training strategy that treats prompts as dynamic variables to achieve robust fine-tuning, significantly mitigating catastrophic…

The paper introduces Atomic Decomposition and Recombination (ADR), a novel framework that generates genuinely novel and challenging verifiable code tasks, significantly improving the scalability of Re…

The paper empirically evaluates domain-adapted and general-purpose LLMs for structured threat modelling (STRIDE on 5G security), finding that domain adaptation and model size do not guarantee reliable…

The paper introduces SCALR, a novel framework that generates synthetic user-item interaction data from a source domain to augment a target recommendation domain, significantly improving system perform…

The paper presents Tahoe, a system that optimizes Text-to-SQL performance through dynamic data management and hint learning.

The paper analyzes language generation and identification in the limit under bounded memory, showing that memory constraints significantly alter learnability, particularly affecting achievable density…

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

The paper proposes $D^3$, a dynamic graph-constrained scheduling framework that optimizes LLM training order by modeling sample interactions as a dynamic influence graph.

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper introduces a novel LLM-driven evolutionary framework to synthesize admissible, domain-specific pattern generators, enabling optimal classical planning with high performance and interpretabil…

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…