🤖 Agentic AI - teslartifex · Scour

Voluntary Collusion with Secret Tools in Competing LLM Agents 🎯AI Agents

AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents ⏱️Latency Engineering

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems 🤖LLM Inference

Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents 🔮Speculative Decoding

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security 🎯AI Agents

Stateful Inference for Low-Latency Multi-Agent Tool Calling 📡Edge AI

arxiv.org·2d·Hacker News

InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward 🔮Speculative Decoding

Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki 🔍RAG

Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams 🤖LLM Inference

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI 🎯AI Agents

Memory-Induced Tool-Drift in LLM Agents 🎯AI Agents

GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning 🤖LLM Inference

CoRe-Code: Collaborative Reinforcement Learning for Code Generation 🦀Rust Macros

SEAL: Synergistic Co-Evolution of Agents and Learning Environments 🎯AI Agents

CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures 🤖LLM Inference

Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs 🤖LLM Inference

IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization 🤖LLM Inference

STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models 🤖LLM Inference

Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems 📡Edge AI

PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction 🤖LLM Inference

Log in to enable infinite scrolling