arXiv AI
Aug 21
Outcome Monitors: Recovery Affordances for Silent Tool Failures
arXiv:2608. 19303v1 Announce Type: new Abstract: When a tool call times out, the agent sees the failure and can route around it.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv Computer Vision
Aug 21
CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios
arXiv:2608. 19380v1 Announce Type: new Abstract: While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal reasoning required to interpret traffic accidents.
arXiv AI
Aug 21
Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis
arXiv:2608. 19902v1 Announce Type: new Abstract: AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the evidence supports.
arXiv Computation and Language
Aug 21
When Contextual Inference Fails: Cancelability in Interactive Instruction Following
arXiv:2603. 19997v2 Announce Type: replace Abstract: We investigate the separation of literal interpretation from contextual inference in a collaborative block-building tasks, where an agent must resolve underspecified instructions using context.
arXiv AI
Aug 21
MidTool: Mid-training Data Synthesis for Agentic Tool Use
arXiv:2608. 20314v1 Announce Type: new Abstract: Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models.
arXiv Machine Learning
Aug 21
Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
arXiv:2608. 20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption.
arXiv AI
Aug 21
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
arXiv:2607. 21596v2 Announce Type: replace Abstract: Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution.
arXiv AI
Aug 21
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
arXiv:2604. 02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data.
arXiv Computer Vision
Aug 21
A 360-Degree Vision Dataset for Learning Yaw Control on GPS-Denied Micro-UAVs in Disaster-Response-Relevant Environments
arXiv:2608. 19866v1 Announce Type: new Abstract: This paper presents a novel data-driven approach to camera-based autonomy for micro-drones in GPS-denied, radio-challenging indoor environments.
arXiv Computation and Language
Aug 21
ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
arXiv:2508. 00554v5 Announce Type: replace-cross Abstract: In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary market information.
arXiv AI
Aug 21
PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
arXiv:2608. 19861v1 Announce Type: new Abstract: Customer-service LLM agents must follow organizational policy when acting on a user's behalf.
arXiv Computation and Language
Aug 21
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents
arXiv:2608. 19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states.
arXiv AI
Aug 21
PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork
arXiv:2510. 25340v2 Announce Type: replace-cross Abstract: Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems.
arXiv AI
Aug 21
TestifAI: Tomography-Based Testing for Deep Learning Systems
arXiv:2608. 18900v2 Announce Type: replace Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.
arXiv AI
Aug 21
Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
arXiv:2608. 19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents.
arXiv AI
Aug 21
Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems
arXiv:2605. 10555v2 Announce Type: replace Abstract: As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms.
arXiv Computation and Language
Aug 21
FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models
arXiv:2608. 20153v1 Announce Type: new Abstract: Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings.
arXiv AI
Aug 21
From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation
arXiv:2608. 20195v1 Announce Type: cross Abstract: Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents.
arXiv AI
Aug 21
The Third Restructuring of Software Form: From the Three-Tier Architecture to Storage, Models, and Agents
arXiv:2608. 20201v1 Announce Type: new Abstract: Software form has undergone two paradigm shifts since its inception: Software 1.
arXiv AI
Aug 21
Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation
arXiv:2608. 19778v1 Announce Type: cross Abstract: Pedestrian simulators need a behaviour rule for every agent, but privacy usually limits the data for setting one to aggregate statistics, namely zone-level device counts and origin-to-destination (OD) flows, with no individual trajectories.