HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG
arXiv:2602.20926v1 Announce Type: new Abstract: Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based...
NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
arXiv:2602.21172v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense reasoning annotations. In this work, we...
ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling
arXiv:2602.20166v1 Announce Type: cross Abstract: In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and cause them to overlook critical issues, leading to the so-called ''alert fatigue''. A common...
Disentangling Geometry, Performance, and Training in Language Models
arXiv:2602.20433v1 Announce Type: new Abstract: Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estimating downstream performance remains unclear. In this work, we systematically investigate the relationship...
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
arXiv:2602.21534v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This...
Petri Net Relaxation for Infeasibility Explanation and Sequential Task Planning
arXiv:2602.22094v1 Announce Type: new Abstract: Plans often change due to changes in the situation or our understanding of the situation. Sometimes, a feasible plan may not even exist, and identifying such infeasibilities is useful to determine when requirements need adjustment....
Inference-time Alignment via Sparse Junction Steering
arXiv:2602.21215v1 Announce Type: cross Abstract: Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributions without parameter updates. While effective, existing methods rely on dense intervention...
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
arXiv:2602.21218v1 Announce Type: cross Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged...
IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions
arXiv:2602.21226v1 Announce Type: cross Abstract: As millions of Muslims turn to LLMs like GPT, Claude, and DeepSeek for religious guidance, a critical question arises: Can these AI systems reliably reason about Islamic law? We introduce IslamicLegalBench, the first benchmark evaluating...
Corporate Governance in the Age of AI: Board Responsibilities and Best Practices
As AI transforms business operations, corporate boards face new governance challenges requiring updated oversight frameworks and expertise.
ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
arXiv:2602.21228v1 Announce Type: cross Abstract: As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself, especially the latent reasoning...
The Headless Firm: How AI Reshapes Enterprise Boundaries
arXiv:2602.21401v1 Announce Type: cross Abstract: The boundary of the firm is determined by coordination cost. We argue that agentic AI induces a structural change in how coordination costs scale: in prior modular systems, integration cost grew with interaction topology (O(n^2)...
Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation
arXiv:2602.22215v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this gap, this paper proposes a scientific...
Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
arXiv:2602.22302v1 Announce Type: new Abstract: Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification. This gap...
Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?
arXiv:2602.22401v1 Announce Type: new Abstract: AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond to isolated...
Towards Autonomous Memory Agents
arXiv:2602.22406v1 Announce Type: new Abstract: Recent memory agents improve LLMs by extracting experiences and conversation history into an external storage. This enables low-overhead context assembly and online memory update without expensive LLM training. However, existing solutions remain passive and reactive;...
Mirroring the Mind: Distilling Human-Like Metacognitive Strategies into Large Language Models
arXiv:2602.22508v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often exhibit structural fragility in complex reasoning tasks, failing to produce correct answers even after successfully deriving valid intermediate steps. Through systematic analysis, we observe that these failures frequently stem not...
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
arXiv:2602.22638v1 Announce Type: new Abstract: Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is...
RLHFless: Serverless Computing for Efficient RLHF
arXiv:2602.22718v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences. Recent models, such as DeepSeek-R1, have also shown RLHF's potential to improve...
ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
arXiv:2602.22771v1 Announce Type: new Abstract: Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of...
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
arXiv:2602.22839v1 Announce Type: new Abstract: Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic...
Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts
arXiv:2602.22359v1 Announce Type: new Abstract: This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded readings of a single hard case rather than scaling up typological labels. It foregrounds prompt-sensitivity...
Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
arXiv:2602.22424v1 Announce Type: new Abstract: Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across multiple LLMs, we show...
Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads
arXiv:2602.22453v1 Announce Type: new Abstract: Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first investigate retrieval heads in multilingual contexts. In...
Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o
arXiv:2602.22524v1 Announce Type: new Abstract: Dyslexia affects approximately 10% of the global population and presents persistent challenges in reading fluency and text comprehension. While existing assistive technologies address visual presentation, linguistic complexity remains a substantial barrier to equitable access. This...
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
arXiv:2602.22584v1 Announce Type: new Abstract: Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it...
Volume 110 – Issue 3 - Minnesota Law Review
Probing for Knowledge Attribution in Large Language Models
arXiv:2602.22787v1 Announce Type: new Abstract: Large language models (LLMs) often generate fluent but unfounded claims, or hallucinations, which fall into two types: (i) faithfulness violations - misusing user context - and (ii) factuality violations - errors from internal knowledge. Proper...
MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations
arXiv:2602.23184v1 Announce Type: new Abstract: We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks containing over 2,800 conversation turns across 6...
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
arXiv:2602.23197v1 Announce Type: new Abstract: Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on downstream tasks, allowing them to solve...