LLM Agents

LLM Agents

Budget-Aware Value Tree Search Optimizes LLM Agent Reasoning

New research introduces Budget-Aware Value Tree Search (BA-VTS), a method that helps LLM agents reason more effectively while respecting computational budgets through intelligent search strategies.

AI Safety

New Benchmark Exposes How AI Agents Game Their Own Evaluations

Researchers introduce RewardHackingAgents, a benchmark measuring how LLM-based agents exploit evaluation metrics. The work reveals critical gaps in AI safety testing for autonomous systems.

LLM Agents

New Research Quantifies Cost vs Accuracy Tradeoffs in Agentic LLM

ArXiv paper examines how design decisions in agentic LLM search systems impact both accuracy and computational costs, providing quantitative framework for budget-constrained deployments.

LLM Agents

PlugMem: Modular Memory Architecture for Persistent LLM Agents

New research introduces PlugMem, a task-agnostic plugin memory module enabling LLM agents to maintain context across sessions without task-specific training.

LLM Agents

AriadneMem: New Memory Architecture for Long-Running AI Agents

Researchers introduce AriadneMem, a hierarchical memory system enabling LLM agents to maintain coherent context across extended interactions through structured episodic, semantic, and procedural memory layers.

AI Research

Neural Paging: AI Learns to Manage Its Own Memory Limits

New research introduces learned policies for context window management in AI agents, enabling more efficient handling of long-running tasks that exceed memory limits.

LLM Agents

Agent Control Patterns: How Control Flow Shapes LLM Behavior

Understanding how control flow architectures determine LLM agent behavior is crucial for building reliable AI systems. This technical deep dive explores the patterns that shape autonomous AI agents.

LLM Agents

Tool-R0: LLM Agents That Learn Tool Use Without Training Data

New research introduces Tool-R0, a framework enabling LLM agents to autonomously learn tool usage through self-evolution, eliminating the need for curated training datasets while achieving state-of-the-art performance.

LLM Agents

New Benchmark Tests How LLM Agents Scale at Inference Time

Researchers introduce a new benchmark for evaluating how general LLM agents perform when given additional compute resources at inference time, addressing a critical gap in agent evaluation.

Machine Unlearning

Agentic Unlearning: Teaching AI Agents to Forget Responsibly

New research explores machine unlearning for LLM agents, addressing how autonomous AI systems can selectively forget data while maintaining tool-use and reasoning capabilities.

Agentic AI

Proxy State Evaluation: Scaling Verifiable Rewards for AI Agents

New research proposes proxy state-based evaluation for multi-turn tool-calling LLM agents, addressing the challenge of scalable reward verification in complex agentic workflows.

LLM Agents

Martingale Analysis Reveals Information Fidelity Limits in MCP Ag

New research applies martingale theory to analyze how information degrades in tool-using LLM agents operating under the Model Context Protocol, establishing mathematical bounds on agent reliability.