When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges

SwiftMem has been introduced as a query-aware agentic memory system designed to enhance the efficiency of large language model (LLM) agents by enabling sub-linear retrieval through specialized indexing techniques. This system addresses the limitations of existing memory frameworks that rely on exhaustive retrieval methods, which can lead to significant latency issues as memory storage expands.

PrivGemo has been introduced as a privacy-preserving framework designed for knowledge graph (KG)-grounded reasoning, addressing the risks associated with using private KGs in large language models (LLMs). This dual-tower architecture maintains local knowledge while allowing remote reasoning through an anonymized interface, effectively mitigating semantic and structural exposure.

A new offline reinforcement learning (RL) framework named STO-RL has been proposed to enhance policy learning from pre-collected datasets, particularly in long-horizon tasks with sparse rewards. By utilizing large language models (LLMs) to generate temporally ordered subgoal sequences, STO-RL aims to improve the efficiency of reward shaping and policy optimization.

The introduction of Surgical Refusal Ablation (SRA) aims to enhance the safety of language models by refining their refusal capabilities, minimizing collateral damage and distribution drift caused by traditional methods. SRA achieves this by creating a registry of independent Concept Atoms and utilizing ridge-regularized spectral residualization to produce a clean refusal direction.

The introduction of LoFT-LLM, a novel forecasting pipeline, aims to enhance time-series predictions in finance and energy sectors by integrating low-frequency learning with large language models (LLMs). This approach addresses challenges posed by limited training data and high-frequency noise, allowing for more accurate long-term trend analysis.