Agents

LLM agents and the systems around them: harnesses and orchestration, tool use and MCP, multi-agent systems, agent memory and planning

600 articles · page 12 of 13

Agents

Personalizing agents through cross-session interaction data boosts task success

Wang et al. propose TAHI (test-time adaptation through human-agent interaction), which leverages a user's cross-session interaction history to update agent context and weights while maintaining an evolving rubric that captures personal evaluation criteria. Applied to writing and visual creation across 30 individuals, the adapted agents outperformed non-adapted baselines on individual tasks, and part of the personalization gains transferred to other users.

Agents

Graph-based policy constrains LLM agents for topology-aware incident response

Vallabhaneni, Cagwin, and Wild built a security-operations architecture in which a graph encoder and reinforcement-learning policy analyze enterprise authentication activity instead of placing the full network state into an LLM’s context. On public cyber-security data and an Indiana University computing cluster, the system achieved 0.91 precision and 0.87 recall on labeled red-team events, with a median 6.3-second end-to-end response cycle.

Agents

Dual-brain memory keeps real-time speech agents accurate and emotionally aware

VoiceMem is a dual-stream memory architecture for duplex speech language models, pairing a factual left brain for personal information with an emotional right brain for affect and persona. The authors show that top-5 retrieval beats Mem0 at top-200 by nearly 30 points, and that retrieval completes in 134 ms, within voice-activity-detection latency. The result is a practical memory foundation for real-time, personalized, emotionally aware spoken interaction.

Agents

Separating state tracking from actions improves multi-turn tool reliability

Guo et al. introduce a structured tool-use policy that separates reconstructing task state, deciding whether to act, specifying an admissible action, and producing the final output. Across multi-turn, multi-tool, and incomplete-information evaluations, the authors report more reliable task completion than direct function calling and ReAct, especially for smaller models and tasks dependent on earlier context.