arXiv AI
Jun 17
Dissecting model behavior through agent trajectories
arXiv:2606. 17454v1 Announce Type: new Abstract: AI agent performance is not just a modeling problem, it is fundamentally a systems problem.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jun 17
Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty
arXiv:2606. 17312v1 Announce Type: new Abstract: Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning.
arXiv Machine Learning
Jun 17
Rethinking Groups in Critic-Free RLVR
arXiv:2606. 17250v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central paradigm for post-training large language models.
arXiv AI
Jun 17
In-Context Environments Induce Evaluation-Awareness in Language Models
arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
arXiv Machine Learning
Jun 17
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
arXiv:2606. 17182v1 Announce Type: new Abstract: Multi-agent LLM systems share state through memory stores, vector indices, and tool registries.
arXiv AI
Jun 17
Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models
arXiv:2606. 18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment.
arXiv AI
Jun 17
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
arXiv:2606. 17830v1 Announce Type: cross Abstract: Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence.
arXiv Machine Learning
Jun 17
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
arXiv:2606. 18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners.
arXiv AI
Jun 17
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
arXiv:2510. 19838v2 Announce Type: replace Abstract: Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions.
arXiv AI
Jun 17
Discrete Autoregressive Transformer for Generative Mechanism Synthesis
arXiv:2606. 17409v1 Announce Type: cross Abstract: Planar path synthesis requires mechanisms whose coupler curves match a prescribed trajectory; the mapping from curve to linkage is inherently one-to-many across four-, six-, and eight-bar topologies.
arXiv Machine Learning
Jun 17
Beyond Visual Cues: CoT-Enhanced Reasoning for Semi-supervised Medical Image Segmentation
arXiv:2606. 17958v1 Announce Type: cross Abstract: Semi-supervised medical image segmentation has emerged as a dominant research problem in medical image analysis, mitigating annotation scarcity by leveraging consistency regularization on unlabeled data.
arXiv AI
Jun 17
Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning
arXiv:2606. 17591v1 Announce Type: new Abstract: Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes.
arXiv AI
Jun 17
Enhancing Pathological VLMs with Cross-scale Reasoning
arXiv:2606. 17412v1 Announce Type: cross Abstract: Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher magnification for accurate diagnosis.
arXiv AI
Jun 17
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization
arXiv:2606. 17915v1 Announce Type: cross Abstract: Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring.
arXiv AI
Jun 17
Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications
arXiv:2606. 18068v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) and multi-agent systems have driven the rise of Agentic AI, showing promise for medical reasoning.
arXiv AI
Jun 17
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
arXiv:2606. 18037v1 Announce Type: new Abstract: Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and formulary tools.
arXiv AI
Jun 17
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
arXiv:2606. 17057v1 Announce Type: cross Abstract: Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text--image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones.
arXiv AI
Jun 17
NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama
arXiv:2606. 17391v1 Announce Type: cross Abstract: Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail.
arXiv AI
Jun 17
Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
arXiv:2606. 17406v1 Announce Type: cross Abstract: Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes.
arXiv AI
Jun 17
LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams
arXiv:2606. 17798v1 Announce Type: cross Abstract: Despite the remarkable progress of Video Large Language Models (Video-LLMs), current online architectures still struggle to simultaneously process continuous video streams, decide autonomously when to respond, and preserve long-horizon contextual memory.