Ax Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Wenzhuo Xu, Dongdong Yang, Deyue Zhang, Quanchen Zou 9d ago

ElephantAgent: Contextual State Continuity in Agentic Systems

ElephantAgent: framework for maintaining verifiable contextual state continuity in agentic systems under tool and memory poisoning attacks.

Ax Zitong Shi, Yixuan Tang, Anthony Kum Hoe Tung 9d ago

A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory

A-TMA: method to address ghost memory failures in LLM agent long-term memory systems tracking state changes and fact transitions.

Ax Yue Zhang, Sihan Chen, Ziwen Huang, Hanyun Cui, Kangye Ji, Zhi Wang 9d ago

Atomic Task Graph: A Unified Framework for Agentic Planning and Execution

Atomic Task Graph framework for LLM-based agent planning and execution handling multi-step tasks without scaling or fine-tuning.

Ax Hamed Babaei Giglou, Jennifer D'Souza, Andrei Aioanei, Nandana Mihindukulasooriya, S\"oren Auer 9d ago

OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models

OntoLearner: modular Python library for automated ontology learning from text using LLMs with systematic evaluation framework.

Ax Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li 9d ago

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

Methods for continuous knowledge editing in multimodal LLMs with controlled scope to minimize disruption to unrelated behaviors.

Ax Xue Qin, Simin Luan, Cong Yang, Zhijun Li 9d ago

Episodic-to-Semantic Consolidation Without Identity Drift

Research on memory consolidation in long-running AI agents while preserving identity and audit compliance without changing agent behavior.

Ax Jiangdi Ru, Bing Li, Yage Huang, Ding Wang, Keru Hua 9d ago

Traceable Fault Diagnosis for Battery Energy Storage Systems via Retrieval-Augmented Multi-Agent O&M Assistant

Traceable fault diagnosis system for battery storage using retrieval-augmented multi-agent assistant to combine alarms, measurements, topology and maintenance data.

Ax Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang 9d ago

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

InduceKV enables fixed-footprint continual adaptation of MLLMs by storing task-specific updates in induced KV memories without modifying backbone model.

Ax Qianyu Chen, Canran Xiao, Runxuan Tang 9d ago

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

Studies hidden forgetting in continual multimodal learning where standard metrics miss degradation of visual and textual grounding despite maintained answer accuracy.

Ax Yueqi Song, Lintang Sutawika, Jiarui Liu, Lindia Tjuatja, Jiayi Geng, Yunze Xiao, Daniel Lee, Aditya Bharat Soni, Vincent Lo, Xiang Yue, Graham Neubig 9d ago

PACE: A Proxy for Agentic Capability Evaluation

PACE shows that cheap non-agentic LLM benchmark performance can accurately predict expensive agentic benchmark results, enabling cost-effective agent capability evaluation.

Ax Hiroki Arimura 9d ago

Algebraic Model Counting for Global Analysis of Optimal Decision Trees

ADTC framework for exhaustive analysis of optimal decision trees using algebraic model counting for global explainability and reliability assessment.

Ax Ya Gao, Pekka Marttinen 9d ago

Evidence-State Rewards for Long-Context Reasoning

Maven is an RL framework with editable evidence memory for long-context reasoning, defining evidence-state value and reward functions for intermediate reasoning steps.

Ax Tomoshi Iiyama, Masahiro Suzuki, Yutaka Matsuo 9d ago

SUNTA: Hierarchical Video Prediction with Surprise-based Chunking

SUNTA uses surprise-based chunking in hierarchical state-space models for long-horizon video prediction, aligning chunk boundaries with intrinsic temporal structure.

Ax Misha Sulpovar (PromptOwl, LLC), Benn R. Konsynski (Goizueta Business School, Emory University), Qaish Kanchwala (IBM Research), Gabe Goodhart (IBM Research) 9d ago

ContextNest: Verifiable Context Governance for Autonomous AI Agent

ContextNest formalizes context governance for autonomous AI agents, providing open spec for knowledge vaults with provenance, versioning, integrity, and traceability.

Ax Xingtao Zhao, Tian Yang, Han Jiang 9d ago

Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training

Domain-specific post-training of LLMs for Scientific Fitness Coaching, addressing knowledge gaps in general-purpose models for specialized fitness scenarios.

Ax Atharva Hans, Ilias Bilionis 9d ago

Coding-agents can replicate scientific machine learning papers

Paper-replication workflow enables coding agents to replicate computational claims from scientific ML papers and verify if generated evidence supports claims.

Ax Shuo Ren, Yaohui Han, Yifan Shi, Libo Shen, Haodong Lu, Dongfang Wu, Rongliang Fu, Bei Yu, Tsung-Yi Ho 9d ago

A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction

A²utoLPBench is an auto-generated benchmark for testing LLM-driven agents on linear programming problems using inverse-KKT construction to avoid data leakage.

Ax Samiha A. Ismail, Fan X. Chen, Ali Merali 9d ago

A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks

Rubric-based evaluation of frontier LLMs on clinician-authored clinical reasoning tasks, showing performance remains low on difficult open-ended scenarios.

Ax Temitayo Olamilekan Ogunsusi, Lijun Qian, Xishuang Dong 9d ago

UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development

UA-ChatDev adds uncertainty awareness to multi-agent software development frameworks to mitigate hallucination propagation across role-based agent collaboration.

Ax Ravi Kant Sharma 9d ago

Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks

Guard Rail Validation framework intercepts AI agent inference outputs in autonomous telecom networks to validate decisions before triggering live state changes.

Ax Zhanming Shen, Jintao Tong, Shaotian Yan, Chen Shen, Hao Chen, Wentao Ye, Xiaomeng Hu, Rui Miao, Haobo Wang, Junbo Zhao, Gang Chen, Jieping Ye 9d ago

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

Purified OPSD improves on-policy self-distillation for long chain-of-thought reasoning by preserving reflective capabilities while providing token-level supervision.

Ax Seren Yenikent, Jack Vinijtrongjit, Katherine Ng 9d ago

Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support

Multi-agent swarm system for mental health support in low-resource settings using dynamic emotional state calibration and multimodal interfaces.

Ax Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang 9d ago

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

AgenticSTS is a testbed for evaluating long-horizon LLM agents with bounded memory contracts, isolating effects of memory components on agent decision-making.

Ax Wanyun Cui 9d ago

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets

HOLA adds hippocampal-inspired exact memory to linear attention models to recover facts that get overwritten in compressed recurrent states, improving needle-in-haystack recall.

Ax Haonan Huang 9d ago

Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics

Autonomous research agent pipeline for computational physics that handles underdocumented toolchains and validates against external literature to avoid hallucinations.

Ax Xi Fang, Weijie Xu, Yingqiang Ge, Yuhui Xu, Stephanie Eckman, Chandan K. Reddy 9d ago

DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models

DRIFTLENS measures how personalization in LLMs changes reasoning trajectories, not just outputs, when user memory is injected into prompts for open-ended questions.

Ax Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi 9d ago

Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems

Hardware-enforced semantic coordination framework for safety-critical autonomous systems integrating LLMs, world models, and specialized architectures.

Ax Thomas Winninger 9d ago

Steerability via constraints: a substrate for scalable oversight of coding agents

Access control and network policies from human engineering teams transfer to coding agents, providing cheaper oversight than agentic scaffolding.

Ax Thomas Winninger 9d ago

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

RFM-AGOP efficiently extracts multi-dimensional refusal subspaces in LLMs for safety and interpretability with reduced computational cost.

Ax Xianhui Meng, Zirui Song, Yuchen Zhang, Li Zhang, Yongxuan Lv, Xiuying Chen, Kun Wang, Yan Luo, Kai Chen, Hangjun Ye, Long Chen, Jun Liu, Xiaoshuai Hao 9d ago

Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

SPG-Layout uses LLMs for text-driven 3D indoor scene synthesis in non-Manhattan environments by modeling non-orthogonal spatial relationships.

Ax Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J. Rodriguez-Martinez, Lorena Otero-Cerdeira 9d ago

Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach

GPT, Claude, Gemini and GLM are evaluated on grading Linux/bash exam responses, handling partial credit and solution equivalence better than rule-based systems.

Ax Zhilin Wang, Han Song, Runzhe Zhan, Jusen Du, Jiacheng Chen, Tianle Li, Qingyu Yin, Yulun Wu, Zhennan Shen, Tong Zhu, Yanshu Li, Guanjie Chen, Derek F. Wong, Yafu Li, Yu Cheng, Yang Yang 9d ago

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

EvoPolicyGym evaluates autonomous agents' ability to improve policies through feedback in interactive environments with controlled evaluation methodology.

Ax Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah, Shahriar Noroozizadeh 9d ago

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

Dual-channel debate framework studying how social structure affects LLM agent communication with public and off-the-record channels.

Ax Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei, Zhining Liu, Lingjie Chen, Ismini Lourentzou, Hanghang Tong, Jingrui He 9d ago

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

ReContext method for long-context reasoning using recursive evidence replay to improve LLM utilization of relevant information in extended contexts.

Ax Mona Schirmer, Metod Jazbec, Alexander Timans, Christian Naesseth, Maja Waldron, Eric Nalisnick 9d ago

Online Safety Monitoring for LLMs

Real-time safety monitoring method for LLMs using verifier signals with risk-calibrated thresholding to detect unsafe outputs at deployment.

Ax Josh Hills, Ida Caspary, Asa Cooper Stickland 9d ago

Distributed Attacks in Persistent-State AI Control

Studies attack surface of persistent-state AI coding agents shipping code iteratively across sessions; introduces Iterative VibeCoding for AI control.

Ax Amirreza Esmaeili, Fatemeh Fard 9d ago

TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models

TokenScope interactive tool for token-level explainability in LLM code generation, providing decoding-time signals and uncertainty measures.

Ax Yining She, Yiliang Liang, Eunsuk Kang 9d ago

Safeguarding LLM Agents from Misalignment through Provenance Analysis

Framework for safeguarding LLM agents from misalignment through provenance analysis of tool invocations against user intent.

Ax Shen Han, Yuyang Wu 9d ago

Kara: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression

Kara system for efficient reasoning LLM serving via sliding-window KV cache compression to reduce decoding latency and memory overhead.

Ax Priyam Mazumdar, Yurii Halychanskyi, Steven Guo, Mark Hasegawa-Johnson, Volodymyr Kindratenko 9d ago

SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings

SPARCLE method for speaker-aware representations in speech synthesis using contrastive learning with grapheme-based models.

Ax Tung-Ling Li, Hongliang Liu, Yuhao Wu 9d ago

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

Identifies BPE tokenization fragmentation of safety-critical words as exploitable gap in LLM alignment, tested on five model families.

Ax Dekun Yang 9d ago

Prompt Framing Distorts Count-Based Evaluation of LLM Error Detection: Evidence from Numeric Anchoring

ErrorBench stress-test protocol showing prompt framing distorts count-based F1 evaluation of LLM error detection without improving span localization.

Ax Yaxin Gao, Yao Lu, Jinhong Deng, Jiaqi Nie, Zhe Tang, Jian Zhang, Zhaowei Zhu, Shanqing Yu, Qi Xuan, Joey Tianyi Zhou 9d ago

Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning

RAGP method for prompt compression using graph pruning guided by Lévy walks, capturing distributed information across syntactic and semantic relations.

Ax Yeji Park, Jiwon Tark, Taesik Gong 9d ago

ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

ExPerT framework for personalizing LLM responses using query-wise semantic and keystroke behavioral cues to adapt to user domain expertise.

Ax Firoz Shaik, Mateus Pican\c{c}o Lima Gomes, Tanvir Aumi, Jingci Wang, Milos Milunovic, Filip Basara, Ivana Jovanovic, Vishwas Suryanarayanan, Neha Nandan Kenkare, Weiyao Xie, Zhipeng Han, Zheng Zhang, Waleed Shahid, Jay Rathi, Russell Scherer, Thong Q. Nguyen, Michael Bentley, Tamara Stankovic, Rasika Chakravarthy, Vishal Chowdhary 9d ago

Office Comprehension Benchmark

Introduces Office Comprehension Benchmark for evaluating LLMs on Word, Excel, PowerPoint comprehension across native file formats and variants.

Ax Aastha Sapkota, M. G. Sarwar Murshed 9d ago

LLMs as Teaching Assistants for Mathematics Exam Grading: Reliability, and Practical Usability

Evaluates six LLM configurations for grading open-ended mathematics exams, assessing reliability and practical usability with partial-credit rubrics.

Ax Yang Zhao, Yingshuo Li, Zeyu Zhang 9d ago

A Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content

Practice auditing framework for LLM use in knowledge acquisition, code generation, and automation; introduces collective empiricism concept.

Ax Esra D\"onmez, Agnieszka Falenska 9d ago

Structuring the Space of Sociotechnical Alignment

Framework for specifying sociotechnical alignment of AI systems, addressing gap between technical and normative aspects of socially desirable behavior.

Ax Dipayan Sengupta, Saumya Panda, Sandipan Dhar, Dipankar De, Deepika Pandhi, Narayanan B 9d ago

How Indian Dermatologists are Utilizing Artificial Intelligence for Clinical Practice and Workflow Management: A Nationwide Survey with a Special Focus on atopic dermatitis

Nationwide survey of Indian dermatologists on AI adoption for clinical practice and atopic dermatitis workflow management.

Ax Jessica D\'iaz, Sonia Linio, Fernando Pescador, Daniel Martin-Fabiani 9d ago

Beyond Detection: Redesigning Assessment and Governande of Generative AI at the Universidad Polit\'ecnica de Madrid (UPM)

Survey of how Universidad Politécnica de Madrid is redesigning institutional policies and governance around generative AI use.