arXiv AI
1d ago
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
arXiv:2608. 15265v1 Announce Type: new Abstract: Constructing an interactive 3D open world from a user query is important.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
1d ago
ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning
arXiv:2608. 15291v1 Announce Type: new Abstract: Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while future promotions, holidays, price changes, and platform interventions provide forward-looking knowledge.
arXiv AI
1d ago
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
arXiv:2608. 15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve.
arXiv AI
1d ago
Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents
arXiv:2608. 15755v1 Announce Type: new Abstract: User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution constraints.
arXiv AI
1d ago
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
arXiv:2608. 15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution.
arXiv AI
1d ago
What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics
arXiv:2608. 16370v1 Announce Type: new Abstract: Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by forcing it to reacquire dropped state while leaving completion statistically unchanged.
arXiv AI
1d ago
HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents
arXiv:2608. 16447v1 Announce Type: new Abstract: Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions.
arXiv AI
1d ago
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
arXiv:2608. 16578v1 Announce Type: new Abstract: AI agents increasingly operate as part of interacting systems rather than in isolation.
arXiv AI
1d ago
Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
arXiv:2608. 16645v1 Announce Type: new Abstract: Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography?
arXiv AI
1d ago
Extend the Safety Horizon for Intelligent Transportation Systems through Semantic-Aware Cooperative Perception
arXiv:2608. 14603v1 Announce Type: cross Abstract: Cooperative perception enables vehicles and infrastructure to exchange sensor data via Vehicle-to-Everything (V2X) communication, extending sensing coverage beyond occlusions and mitigating blind spots.
arXiv AI
1d ago
When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL
arXiv:2608. 14559v1 Announce Type: new Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when?
arXiv AI
1d ago
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.
arXiv AI
1d ago
Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP
arXiv:2608. 14613v1 Announce Type: new Abstract: Modern LLM-agent frameworks increasingly interoperate through standards such as Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Google's Agent2Agent (A2A) protocol for agent delegation and negotiation.
arXiv AI
1d ago
Learning Agent Execution for KV-Cache Management in Agentic Serving
arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.
arXiv AI
1d ago
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
arXiv:2608. 14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support agent learns to sound warm while giving no real help.
arXiv AI
1d ago
Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence
arXiv:2608. 14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or expert belief.
arXiv AI
1d ago
Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid
arXiv:2608. 14943v1 Announce Type: new Abstract: Agent skills are often injected in full on every request, increasing token cost.
arXiv AI
1d ago
Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL
arXiv:2608. 14945v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories.
arXiv AI
1d ago
Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads
arXiv:2608. 15117v1 Announce Type: new Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool invocations, and context expansion.
arXiv AI
1d ago
Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation
arXiv:2608. 14711v1 Announce Type: new Abstract: AI coding agent benchmarks rank agents with the Chen et al.