arXiv AI
Aug 11
MELLON - Multimodal Enhanced LLM for Online Navigation
arXiv:2608. 09121v1 Announce Type: new Abstract: Web navigation agents are capable of addressing various types of tasks on different websites.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Aug 11
EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models
arXiv:2608. 08138v1 Announce Type: cross Abstract: Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training.
arXiv Machine Learning
Aug 11
Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design
arXiv:2602. 00549v2 Announce Type: replace Abstract: While Monte Carlo Tree Search (MCTS) shows promise in Large Language Model (LLM) based Automatic Heuristic Design (AHD), it suffers from a critical over-exploitation tendency under the limited computational budgets required for heuristic evaluation.
arXiv AI
Aug 11
CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models
arXiv:2608. 07621v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primarily designed for an individual single autonomous driving agent with limited support for cooperative perception, reasoning, and planning.
arXiv AI
Aug 11
TREAT: Evaluating Access to Formal Knowledge across Equivalent Mathematical Representations
arXiv:2608. 07540v1 Announce Type: new Abstract: AI systems increasingly operate between flexible input representations and formal objects used by downstream tools.
arXiv AI
Aug 11
Adaptive Two-Level Allocation of a Conserved Capacity Budget Across Locations and Service Classes
arXiv:2608. 07747v1 Announce Type: new Abstract: We study how to share a single conserved capacity budget across many locations and two service classes when demand is uneven, time-varying, and can exceed supply.
arXiv AI
Aug 11
Back to the Future: A workbook time machine for spread sheet creation benchmarks
arXiv:2608. 07873v1 Announce Type: new Abstract: We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting).
arXiv AI
Aug 11
GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
arXiv:2608. 07905v1 Announce Type: new Abstract: Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environmental awareness.
arXiv AI
Aug 11
ZhuLong: Execution-Grounded LLM Agent for EDA Scripting with Offline API Self-Exploration
arXiv:2608. 07925v1 Announce Type: new Abstract: EDA scripting with tool-specific, often undocumented APIs remains a long-tail bottleneck that existing LLMs fail to address.
arXiv AI
Aug 11
AndroidReality: How Far Are Mobile Agents from the Real World?
arXiv:2608. 07775v1 Announce Type: new Abstract: Mobile agents have achieved promising results on clean online benchmarks such as AndroidWorld, yet their performance often degrades sharply in real-world deployment due to environmental variations and imperfect interface conditions.
arXiv AI
Aug 11
Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation
arXiv:2608. 08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation.
arXiv AI
Aug 11
SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User Requests
arXiv:2608. 08640v1 Announce Type: new Abstract: Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge.
arXiv AI
Aug 11
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
arXiv:2608. 08264v1 Announce Type: new Abstract: Large language model agents are becoming operational interfaces to files, memories, registries, and external tools.
arXiv AI
Aug 11
Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning
arXiv:2608. 08303v1 Announce Type: new Abstract: Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks.
arXiv AI
Aug 11
PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue
arXiv:2608. 07631v1 Announce Type: cross Abstract: LLM-based full-duplex voice services allow users to speak while the assistant is responding.
arXiv AI
Aug 11
Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs
arXiv:2608. 08506v1 Announce Type: new Abstract: Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-level accuracy.
arXiv AI
Aug 11
Smart Compaction: Predicting Compaction Utility from Lakehouse Table Metadata
arXiv:2608. 08639v1 Announce Type: new Abstract: Open lakehouse table formats accumulate small data files over time, which degrades query performance.
arXiv AI
Aug 11
Branch2Skill: Efficient Skill Evolution Through Reasoning Trees
arXiv:2608. 08677v1 Announce Type: new Abstract: Skill evolution improves agent skills through feedback over time, with failed trajectories often providing informative signals by revealing incomplete or misleading behaviors.
arXiv AI
Aug 11
EnergyBridge: Benchmarking Household Energy Management, User Participation, and Grid Flexibility
arXiv:2608. 08691v1 Announce Type: new Abstract: Residential virtual power plants (VPPs) can provide grid flexibility by shifting household demand, but physical flexibility becomes dependable capacity only when residents authorize a plan and the promised response is delivered.
arXiv Machine Learning
Aug 11
End-to-End Neural Decomposition with Koopman Operators for Time-Series Forecasting
arXiv:2608. 08788v1 Announce Type: cross Abstract: Koopman theory offers a linear-operator view of nonlinear sequence dynamics by lifting observations into a space where evolution is governed by a linear time-invariant Koopman operator.