Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT

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.

Recent research highlights that while KV cache reuse can enhance efficiency in multi-agent large language model (LLM) systems, it can negatively impact the performance of LLM judges, leading to inconsistent selection behaviors despite stable end-task accuracy.

A new framework named VideoHEDGE has been introduced to detect hallucinations in video-capable vision-language models (Video-VLMs), addressing the frequent inaccuracies in video question answering. This system employs entropy-based reliability estimation and semantic clustering to evaluate the correctness of generated answers against video-question pairs.

A recent study has revealed that the group-relative advantage estimator used in Reinforcement Learning from Verifier Rewards (RLVR) is biased, systematically underestimating advantages for difficult prompts while overestimating them for easier ones. This imbalance can lead to ineffective exploration and exploitation strategies in training large language models.

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.

The introduction of Process Relative Policy Optimization (PRPO) aims to enhance policy optimization for large language models (LLMs) by aligning process rewards with outcome rewards, addressing the limitations of existing critic-free methods like GRPO. PRPO provides a more nuanced approach by segmenting reasoning sequences and normalizing feedback, which improves the accuracy of models such as Qwen2.5-Math-1.5B on tasks like MATH500.