💡 AI Assistants - ABQ_Work · Scour

Rosetta Memory: Adaptive Memory for Cross-LLM Agents

🧠LLMs Academic

TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory

🧠LLMs Academic

Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration

🧠LLMs Academic

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

🧠LLMs Academic

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

⚡Concurrency Academic

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

🧠LLMs Academic

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

🧠LLMs Academic

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

🧠LLMs Academic

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

🧠LLMs Academic

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

🧠LLMs Academic

(Auto)formalization is supposed to be easy: Trellis process semantics for spelling out rigorous proofs

🧠LLMs Academic

Benchmarking Open-Ended Multi-Agent Coordination in Language Agents

🧠LLMs Academic

Token Budgets: An Empirical Catalog of 63 LLM-Agent Budget-Overrun Incidents, with an Affine-Typed Rust Mitigation as a Case Study

🦀Rust Academic

Collective Hallucination in Multi-Agent LLMs:Modeling and Defense

🧠LLMs Academic

Harnessing Generalist Agents for Contextualized Time Series

🧠LLMs Academic

Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure

🤖AI Coding Tools Academic

SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models

🧠LLMs Academic

SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling

🧠LLMs Academic

Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents

🤖AI Coding Tools Academic

From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents

🧠LLMs Academic

Log in to enable infinite scrolling