The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

ProactiveLLM introduces a novel framework that enables streaming LLMs to actively decide when to interact with incoming data by leveraging the model's internal states, significantly reducing latency w…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

The paper introduces PlanAudio, a unified LLM-based framework that directly synthesizes natural, composite audio containing speech and sounds from unconstrained free-form text prompts, outperforming e…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

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…

This paper introduces a 'Sleep' paradigm for machine learning models to continually learn and transfer knowledge.

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 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 proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…

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…

The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive…

The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…