AAI News Hub

#llm-agents

13 briefs tagged #llm-agents.

Research

Researchers propose aDSL for agentic 3D creation

The system pairs an agent-centric DSL with a multi-agent loop for more robust 3D program generation.

HF Daily Papers·1d ago
Research

Researchers push structured memory for AI agents

Six new papers propose schema, graph and skill-based systems for more reliable long-term agent memory.

arXiv cs.AI+1 outlet·6d ago
Research

Researchers target memory failures in long-term LLM agents

New papers propose graph, segment and interference methods for maintaining agent memory.

arXiv cs.AI+1 outlet·6d ago
Research

Researchers target LLM exploration beyond temperature

DORA, 3PO and RISE-RL propose new ways to improve exploration in LLM agents and reinforcement learning.

arXiv cs.AI+1 outlet·6d ago
Research

Paper bounds GPU opportunity in LLM-agent control

The study models when agent control paths expose enough concurrent work for GPU execution.

arXiv cs.AI+1 outlet·6d ago
Research

New agent frameworks optimize design tasks with LLM search

AUTO, AutoDesign and SynAct apply iterative LLM agents to code, posters and chip synthesis.

HF Daily Papers+1 outlet·6d ago
Research

Researchers flag backdoor risks in LLM-agent skills

New papers probe how reusable agent skills can be poisoned, compressed and evolved.

arXiv cs.AI+1 outlet·Aug 11
Research

HarnessOpt-Bench tests LLMs on agent harness optimization

The benchmark measures how LLMs improve prompts, tools, memory and orchestration around agents.

arXiv cs.AI+1 outlet·Aug 7
Research

New papers target scalable training for LLM agents

EnvACE and State2State reduce reliance on manual environments, expert trajectories and task design.

arXiv cs.AI+1 outlet·Aug 7
Research

Researchers target prompt injection in LLM agents

Two papers propose adaptive defenses and automated red-teaming for agent security.

arXiv cs.AI+1 outlet·Aug 6
Research

Researchers target prompt injection risks in LLM agents

New papers test attacks and defenses for agents, including robotic systems and indirect prompt injection.

arXiv cs.AI+1 outlet·Aug 6
Research

Researchers target sparse rewards in agentic RL

New arXiv papers propose self-distillation methods for denser credit assignment in LLM agents.

arXiv cs.AI+1 outlet·Aug 4
Research

New papers test self-distillation for LLM reinforcement learning

Studies propose ICE and OCSD while warning that privileged-information teachers can fail on harder tasks.

arXiv cs.AI+1 outlet·Aug 4