Related papers: SE-Bench: Benchmarking Self-Evolution with Knowled…

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model…

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…

While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate remains underexplored. This paper operationalizes the…

Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we…

Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments, benchmarks stabilize the dominant paradigm by narrowing what counts as progress. Over…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

Deep reinforcement learning suffers from catastrophic forgetting and sample inefficiency making it less applicable to the ever-changing real world. However, the ability to use previously learned knowledge is essential for AI agents to…

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…

AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially…

Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source…

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Large Language Models (LLMs) demonstrate remarkable capabilities in leveraging comprehensive world knowledge and sophisticated reasoning mechanisms for recommendation tasks. However, a notable limitation lies in their inability to…

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing…

AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart…

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…

Self-evolution, the ability of agents to autonomously improve their reasoning and behavior, is essential for the embodied domain with long-horizon, real-world tasks. Despite current advancements in reinforcement fine-tuning (RFT) showing…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…

Recent information extraction approaches have relied on training deep neural models. However, such models can easily overfit noisy labels and suffer from performance degradation. While it is very costly to filter noisy labels in large…