Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments violate all these assumptions: user typos propagate into hallucinated tool names, a misconfigured request timeout can stall an agent indefinitely, and duplicate tool names acro...
Xiaolin Zhou, Aojie Yuan, Zheng Luo et al.· 0 citations
Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs)...
Hongwei Zhang, Qiqiang Zhong, Junfeng Shu et al.· 0 citations
We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs are organized along four causal levels (state, intervention, counterfactual, decision) instantiating Pearl's ladder of causation, and span five answer formats: four str...
Yanis Merzouki, Coral Izquierdo, Matei Ignuta-Ciuncanu et al.· 0 citations
Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous evaluation of scientific tool use remains limited. In chemistry, recent agents can plan syntheses and invoke domain-specific tools, but evaluations often rely on curat...
Yuyang Wu, Yue Huang, Shuaike Shen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematically study this question, we introduce DEAF (Diagnostic Evaluation of...
Jiaqi Xiong, Yunjia Qi, Qi Cao et al.· 0 citations
NeuronSpark is a self-attention-free language model built around input-dependent spiking membrane dynamics, where each neuron's decay rate, gain, and firing threshold adapt to the current token content, which enables billion-scale pretraining from random initialization without backbone transfer, conversion, conversion,...
As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AutoControl Arena, an automated framework for frontier AI risk evaluation built o...
Changyi Li, Pengfei Lu, Xudong Pan et al.· 0 citations
Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicability in privacy-sensitive clinical settings. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framewor...
Yichen Wu, Kailong Fan, Sangjoon Park et al.· 0 citations
NLP systems increasingly aggregate claims from retrieved passages, documents, and generated reasoning steps. Yet current factuality methods mostly verify claims individually or compare pairs of claims, leaving open the question of whether the entire aggregated claim set can be retained coherently. This misses a fundame...
Paul He, Elke Kirschbaum, Shiva Kasiviswanathan· 0 citations
On-device LLM inference is increasingly important for edge platforms but remains challenging due to high computational and memory demands and tight resource constraints. Modern applications often involve long prompts. Although compact models reduce linear-layer costs through weight compression, attention remains largel...
Jiawen Qi, Jiayu Liu, Chang Gao et al.· 0 citations
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model w...
Bhanu Tokas, Rahul Nair, Rockwell Jackson et al.· 0 citations
While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Mean Squared Error (MSE), but differences in datasets, backbon...
Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev et al.· 0 citations
