arXiv AI
Jul 15
Tracing Agentic Failure from the Flow of Success
arXiv:2607. 12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.
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
Jul 15
Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?
arXiv:2607. 12787v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc.
arXiv Machine Learning
Jul 15
Speculate with Memory: Lossless Acceleration for LLM Agents
arXiv:2607. 12236v1 Announce Type: new Abstract: Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle.
arXiv Machine Learning
Jul 15
A Shared Subcircuit Lets LLMs Count Down Across Tasks
arXiv:2607. 12279v1 Announce Type: cross Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table.
arXiv AI
Jul 15
From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data
arXiv:2607. 12175v1 Announce Type: cross Abstract: X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction.
arXiv Machine Learning
Jul 15
A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs
arXiv:2602. 19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets.
arXiv Machine Learning
Jul 15
Watermark Forensics for Generative Models: An Information-Theoretic Perspective
arXiv:2607. 13003v1 Announce Type: cross Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made.
arXiv AI
Jul 15
Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs
arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
arXiv AI
Jul 15
The Benjamini--Hochberg Procedure Can Fail to Control the FDR for Correlated Two-Sided Gaussian Tests
arXiv:2607. 12208v1 Announce Type: cross Abstract: We show that the Benjamini--Hochberg procedure can fail to control the false discovery rate (FDR) at its nominal level for correlated two-sided Gaussian $p$-values.
arXiv AI
Jul 15
Human-AI Agent Interaction as a Neuroplastic Training Environment
arXiv:2607. 12823v1 Announce Type: new Abstract: Interaction with AI agents has become one of the most frequent activities of everyday digital life.
arXiv Machine Learning
Jul 15
Auditable Context-Aware HFMD Forecasting with Structured LLM Agents
arXiv:2511. 23276v2 Announce Type: replace Abstract: Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and policy or surveillance reports.
arXiv Machine Learning
Jul 15
When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
arXiv:2510. 20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasoning and provide effective supervision to superhuman LLMs.
arXiv Machine Learning
Jul 15
Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
arXiv:2512. 15748v2 Announce Type: replace Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology, palynology, evolutionary biology, systematics, and phylogenetics.
arXiv Machine Learning
Jul 15
APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model
arXiv:2603. 08862v2 Announce Type: replace-cross Abstract: Autonomous navigation in highly constrained environments remains challenging for mobile robots.
arXiv Machine Learning
Jul 15
AMUSE: Anytime Muon with Stable Gradient Evaluation
arXiv:2605. 22432v2 Announce Type: replace Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimization removes explicit schedules via iterate averaging, and Muon improves the update geometry by orthogonalizing momentum for matrix parameters.
arXiv AI
Jul 15
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
arXiv:2607. 12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists.
arXiv AI
Jul 15
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
arXiv:2603. 28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations.
arXiv AI
Jul 15
Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs
arXiv:2607. 12605v1 Announce Type: cross Abstract: Large language models (LLMs) have improved automated program repair (APR), but two limitations remain.
arXiv Machine Learning
Jul 15
SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning
arXiv:2607. 12042v1 Announce Type: cross Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation.
arXiv AI
Jul 15
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
arXiv:2606. 29537v2 Announce Type: replace Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.