Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads to significant computational costs and training latency, but also yields sparse rewards that hinder optimization efficiency. To address these challenges, we propose Latent-GRPO, a framework that derives intrinsic rewards directly from latent space geometry. Crucially, our empirical analysis reveals a compelling geometric property: terminal token representations of correct reasoning trajectories form dense clusters with high intra-class similarity, whereas incorrect trajectories remain scattered as outliers. In light of this discovery, we introduce the Iterative Robust Centroid Estimation (IRCE) algorithm, which generates dense, continuous rewards by mitigating magnitude fluctuations via spherical projection and estimating a robust “truth centroid” through iterative aggregation. Experimental results on multiple datasets show that our method maintains model performance while achieving a training speedup of over 2x compared to baselines. Furthermore, extensive results demonstrate strong generalization ability and robustness.

Real-time voice agents face a tension: end-to-end models often lack deep reasoning, while cascaded ASR–LLM–TTS pipelines achieve stronger reasoning but defer LLM inference until after ASR finalizes the transcript, creating an avoidable post–turn-end silent gap. We target this gap under complex spoken requests that admit a relatively determinate answer, and treat it as system-induced rather than communicatively motivated. Existing cascaded streaming strategies attempt to reduce it via mechanical segmentation (e.g., fixed chunks, VAD-based splitting) or speculative generation, but they frequently either break semantic units or waste computation on predictions that must be rolled back. We propose LTS-VoiceAgent, a Listen–Think–Speak framework that explicitly separates when to think from how to reason incrementally. It features a Dynamic Semantic Trigger to detect meaningful prefixes, and a Dual-Role Stream Orchestrator that coordinates a background Thinker (for state maintenance) and a foreground Speaker (for speculative solving). This parallel design enables "thinking while listening" without committing audible content before turn end. We also introduce a Pause-and-Repair benchmark that injects natural disfluencies as a semantic-level streaming stress test. Experiments across VERA, Spoken-MQA, BigBenchAudio, and our benchmark show that LTS-VoiceAgent achieves a stronger accuracy–latency–efficiency trade-off than serial cascaded baselines and existing streaming strategies.

Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and ineffective credit assignment, providing insufficient guidance for individual memory operations. To this end, we propose Fine-Mem, a unified framework designed for fine-grained feedback alignment. First, we introduce a Chunk-level Step Reward to provide immediate step-level supervision via auxiliary chunk-specific question answering tasks. Second, we devise Evidence-Anchored Reward Attribution to redistribute global rewards by anchoring credit to key memory operations, based on the specific memory items utilized as evidence in reasoning. Together, these components enable stable policy optimization and align local memory operations with the long-term utility of memory. Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines, achieving superior success rates across various sub-tasks. Further analysis reveals its adaptability and strong generalization capabilities across diverse model configurations and backbones

High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequence, lacking an intrinsic mechanism to quantify step-wise information gain. This granularity gap manifests in two limitations: inference inefficiency from redundant exploration without explicit guidance, and optimization difficulty due to sparse outcome supervision or costly external verifiers. In this work, we propose CoT-Flow, a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer. Built on this formulation, CoT-Flow enables two complementary methodologies: flow-guided decoding, which employs a greedy flow-based decoding strategy to extract information-efficient reasoning paths, and flow-based reinforcement learning, which constructs a verifier-free dense reward function. Experiments on challenging benchmarks demonstrate that CoT-Flow achieves a superior balance between inference efficiency and reasoning performance.

Multilingual document-grounded dialogue, where the system is required to generate responses based on both the conversation Multilingual context and external knowledge sources. Traditional pipeline methods for knowledge identification and response generation, while effective in certain scenarios, suffer from error propagation issues and fail to capture the interdependence between these two sub-tasks. To overcome these challenges, we propose the application of the SLDT method, which treats passage-knowledge selection as a sequential decision process rather than a single-step decision process. We achieved winner 3rd in dialdoc 2023 and we also validated the effectiveness of our method on other datasets. The ablation experiment also shows that our method significantly improves the basic model compared to other methods.