- Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao · Feb 26, 2026
Automatic Metrics General
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems.
- ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning
Hyeonje Choi, Jeongsoo Lee, Hyojun Lee, Jay-Yoon Lee · Feb 24, 2026
Simulation Env Math
We introduce \ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution.
- Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning
Justin Lovelace, Christian Belardi, Sofian Zalouk, Adhitya Polavaram, Srivatsa Kundurthy · Feb 24, 2026
Llm As JudgeAutomatic Metrics General
Evaluations show STAR-LDM significantly outperforms similar-sized models on language understanding benchmarks and achieves $>70\%$ win rates in LLM-as-judge comparisons for narrative coherence and commonsense reasoning.
- KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge
Alex Robertson, Huizhi Liang, Mahbub Gani, Rohit Kumar, Srijith Rajamohan · Feb 23, 2026
Automatic Metrics General
Existing benchmarks are limited by static and narrow questions, leading to limited coverage and misleading evaluations.
- Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
Wenqiu Tang, Zhen Wan, Takahiro Komamizu, Ichiro Ide · Feb 22, 2026
Automatic Metrics Coding
Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-s
- Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering
Amine Kobeissi, Philippe Langlais · Feb 20, 2026
Automatic Metrics Coding
Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings.
- Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini · Feb 20, 2026
Automatic Metrics General
Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity.
- AIDG: Evaluating Asymmetry Between Information Extraction and Containment in Multi-Turn Dialogue
Adib Sakhawat, Fardeen Sadab, Rakin Shahriar · Feb 19, 2026
Automatic Metrics General
Evaluating the strategic reasoning capabilities of Large Language Models (LLMs) requires moving beyond static benchmarks to dynamic, multi-turn interactions.
- Reinforced Fast Weights with Next-Sequence Prediction
Hee Seung Hwang, Xindi Wu, Sanghyuk Chun, Olga Russakovsky · Feb 18, 2026
Automatic Metrics General
Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context length.
- Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik · Feb 16, 2026
Automatic Metrics General
Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.
- From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design
Sha Li, Stefano Petrangeli, Yu Shen, Xiang Chen · Feb 14, 2026
Simulation Env Coding
We introduce LaySPA, a reinforcement learning framework that equips large language models (LLMs) with explicit and interpretable spatial reasoning for content-aware graphic layout design.
- Document Reconstruction Unlocks Scalable Long-Context RLVR
Yao Xiao, Lei Wang, Yue Deng, Guanzheng Chen, Ziqi Jin · Feb 9, 2026
Automatic Metrics Coding
However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.
- How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
Yuxuan Li, Leyang Li, Hao-Ping Lee, Sauvik Das · Feb 6, 2026
Simulation Env General
A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form attitudes toward and behave in response to security and privacy (S&P) threats.
- Embodied Task Planning via Graph-Informed Action Generation with Large Language Model
Xiang Li, Ning Yan, Masood Mortazavi · Jan 29, 2026
Simulation Env Coding
While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning.
- Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Xinyu Zhu, Yuzhu Cai, Zexi Liu, Bingyang Zheng, Cheng Wang · Jan 15, 2026
Simulation Env General
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanni
- KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification
Erfan Nourbakhsh, Nasrin Sanjari, Ali Nourbakhsh · Dec 9, 2025
Automatic Metrics MedicineCoding
Age-related macular degeneration (AMD) and choroidal neovascularization (CNV)-related conditions are leading causes of vision loss worldwide, with optical coherence tomography (OCT) serving as a cornerstone for early detection and managemen
- Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury · Nov 10, 2025
Automatic Metrics Coding
On the Episodic Memory Benchmark (EpBench) \cite{huet_episodic_2025} comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to \textbf{20\%}.
- Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
Mohammad Tavakoli, Alireza Salemi, Carrie Ye, Mohamed Abdalla, Hamed Zamani · Oct 31, 2025
Automatic Metrics General
Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coh
- Structure-Augmented Reasoning Generation
Jash Rajesh Parekh, Pengcheng Jiang, Jiawei Han · Jun 10, 2025
Automatic Metrics General
Extensive experiments on open-domain QA benchmarks and specialized reasoning datasets in finance and medicine demonstrate that SARG significantly outperforms state-of-the-art flat-context RAG baselines in both factual accuracy and reasoning
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao · Apr 7, 2025
Automatic Metrics Math
We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-cont
- EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents
Sara Fish, Julia Shephard, Minkai Li, Ran I. Shorrer, Yannai A. Gonczarowski · Mar 24, 2025
Simulation Env General
We develop evaluation methods for measuring the economic decision-making capabilities and tendencies of LLMs.
