arXiv cs.AI
The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
The article discusses the Compressive Knowledge Graph Hypothesis, which explores the significance of various graph…
Hub / Ai Research
ai-research · WeSearch
Ai Research news.
Page 6 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.
arXiv cs.AI
Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering
The article discusses a new framework called DualGraph designed for semi-structured question answering. It combines…
arXiv cs.AI
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
The paper discusses the limitations of retrieval-augmented language models (LLMs) in handling contradictory evidence.…
arXiv cs.AI
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 is a new benchmark designed to evaluate personalized and proactive agents in long-term user…
arXiv cs.AI
StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning
The paper presents StepOPSD, a new framework for improving reinforcement learning in multi-turn agents. This framework…
arXiv cs.AI
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
The paper introduces ICCU, a framework for in-context continual unlearning in machine learning. It addresses…
arXiv cs.AI
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
The paper discusses advancements in Vision-Language Models (VLMs) for mobile GUI navigation. It introduces HyperTrack,…
arXiv cs.AI
Position: AI Safety Requires Effective Controllability
The paper discusses the importance of controllability in AI safety, arguing that alignment alone is insufficient. It…
arXiv cs.AI
Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
The paper presents a novel approach called Counteraction-Aware Multi-Teacher On-Policy Distillation (CaMOPD) aimed at…
arXiv cs.AI
Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
The article discusses a new framework called SCENE that aims to contextualize broad biomedical knowledge into…
arXiv cs.AI
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
A new system called Chat-ISV has been developed to assist in decision-making regarding volatile organic compounds…
arXiv cs.AI
BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
The article presents BatteryMFormer, a novel approach for forecasting battery degradation trajectories. This method…
arXiv cs.AI
Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
The paper discusses an innovative approach to improve Knowledge Graph Foundation Models (KGFMs) through enhanced…
arXiv cs.AI
ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis
The article introduces ORCA, an interactive copilot designed for optimized root cause analysis. It aims to make causal…
arXiv cs.AI
Generating Robust Portfolios of Optimization Models using Large Language Models
The paper discusses a novel algorithm for generating robust portfolios of optimization models using large language…
arXiv cs.AI
LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
The paper introduces LELA, an end-to-end framework for entity linking that utilizes large language models (LLMs) and…
arXiv cs.AI
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)
The paper discusses a new verification architecture for large language models (LLMs) used in sensitive domains. It…
arXiv cs.AI
Developing a Totally Unimodular Linear Program for Optimal Conformance Checking: When and Why It Complements A*
A new paper introduces a totally unimodular linear program for optimal conformance checking, enhancing the traditional…
arXiv cs.AI
From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework for Legal Indicator Computation
The paper introduces N2I-RAG, a framework aimed at automating the computation of legal indicators from normative…
arXiv cs.AI
TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews
The article introduces TADDLE, a tool designed to detect deficiencies in peer reviews generated by large language…
arXiv cs.AI
On the Detection of Commutative Factors in Factor Graphs: Necessary and Sufficient Conditions
The paper discusses the detection of commutative factors in factor graphs, which are essential for efficient…
arXiv cs.AI
Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
The paper discusses the challenges of aligning large language models (LLMs) with multiple stakeholders who have…
arXiv cs.AI
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
The article introduces Helicase, an autonomous multi-agent LLM system designed for constructing supply chain knowledge…
arXiv cs.AI
What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation
The paper explores the effectiveness of chain-of-thought (CoT) prompting in language models, focusing on probe-time…
arXiv cs.AI
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
The paper discusses the concept of composition collapse in artificial intelligence, where stable factual knowledge…
arXiv cs.AI
LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?
The paper introduces LiveK12Bench, a benchmark designed to evaluate the reasoning abilities of large multimodal models…
arXiv cs.AI
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
The paper discusses the challenges of verifying whether language models rely on retrieved context or their internal…
arXiv cs.AI
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
The paper discusses how chain-of-thought (CoT) in large reasoning models (LRMs) complicates the control of refusal…
arXiv cs.AI
A Dataset of Robot-Patient and Doctor-Patient Medical Dialogues for Spoken Language Processing Tasks
A new dataset named MeDial-Speech has been introduced to enhance spoken language processing in medical consultations.…
arXiv cs.AI
It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
A recent study challenges the assumption that higher-capability LLM models require less structural guidance. The…
arXiv cs.AI
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
The paper discusses advancements in self-evolving large language models (LLMs) for CUDA kernel generation. It…
arXiv cs.AI
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
The article discusses the challenges faced by medical AI agents when using external tools for diagnosis and treatment.…
arXiv cs.AI
MemFail: Stress-Testing Failure Modes of LLM Memory Systems
The paper introduces MemFail, a diagnostic benchmark designed to stress-test the failure modes of memory systems in…
arXiv cs.AI
Completion vs Optimality: Policy Gradient in Long-Horizon Cumulative-Damage Problems
The paper discusses long-horizon decision problems characterized by cumulative damage and the challenges faced by…
arXiv cs.AI
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
The article introduces UnityMAS-O, a general reinforcement learning optimization framework designed for large language…
arXiv cs.AI
Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2
The article discusses a new method called Tail-Aware HiFloat4 for post-training quantization in low-bit text-to-video…
arXiv cs.AI
FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning
The paper presents FAST-GOAL, a method designed to improve the performance of vision-language models like CLIP when…
arXiv cs.AI
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
The article discusses a new method called AGORA for improving prompt compression in large language model (LLM) agents.…
arXiv cs.AI
MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning
The article discusses MedGuideX, a new approach to integrating clinical practice guidelines into large language models…
arXiv cs.AI
MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration
MobileExplorer is a new framework designed to enhance on-device inference for mobile GUI agents. It aims to reduce…
arXiv cs.AI
PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design
PolyFusionAgent is a new multimodal foundation model designed to enhance polymer property prediction and inverse…
arXiv cs.AI
Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning
The paper discusses the importance of distinguishing legally relevant changes in legal AI systems. It introduces a new…
arXiv cs.AI
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
The MiniMax-M2 series introduces a new family of Mixture-of-Experts language models. These models leverage mini…
arXiv cs.AI
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
A recent study evaluates how Large Language Models (LLMs) perform on mathematical reasoning tasks when faced with…
arXiv cs.AI
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
The article discusses a new approach to improving dialogue agents through a method called Calibrated Interactive RL.…
arXiv cs.AI
Advancing Creative Physical Intelligence in Large Multimodal Models
A new paper introduces MM-CreativityBench, a benchmark designed to evaluate creative problem-solving in large…
arXiv cs.AI
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
The paper discusses advancements in Hierarchical Reinforcement Learning (HRL) by focusing on the reuse of skills…
arXiv cs.AI
Automatic Layer Selection for Hallucination Detection
A new study proposes an automated method for selecting layers in large language models to improve hallucination…
arXiv cs.AI
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
The paper titled 'ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence' presents a new…
arXiv cs.AI
Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning
The paper discusses a framework for managing uncertainty in procedural knowledge generated by large language models…