When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching

Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory. This coarse-grained credit assignment fails to distinguish effective tool calls from redundant or erroneous ones, particularly in long-horizon multi-turn scenarios. To address this, we propose MatchTIR, a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation. Specifically, we formulate credit assignment as a bipartite matching problem between predicted and ground-truth traces, utilizing two assignment strategies to derive dense turn-level rewards. Furthermore, to balance local step precision with global task success, we introduce a dual-level advantage estimation scheme that integrates turn-level and trajectory-level signals, assigning distinct advantage values to individual interaction turns. Extensive experiments on three benchmarks demonstrate the superiority of MatchTIR. Notably, our 4B model surpasses the majority of 8B competitors, particularly in long-horizon and multi-turn tasks. Our codes are available at https://github.com/quchangle1/MatchTIR.

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

Reinforcement Learning with Verifiable Rewards (RLVR) is crucial for advancing large-scale reasoning models. However, existing parameter-efficient methods, such as PiSSA and MiLoRA, are designed for Supervised Fine-Tuning (SFT) and do not account for the distinct optimization dynamics and geometric structures of RLVR. Applying these methods directly leads to spectral collapse and optimization instability, which severely limit model performance. Meanwhile, alternative approaches that leverage update sparsity encounter significant efficiency bottlenecks on modern hardware due to unstructured computations. To address these challenges, we propose GeoRA (Geometry-Aware Low-Rank Adaptation), which exploits the anisotropic and compressible nature of RL update subspaces. GeoRA initializes adapters by extracting principal directions via Singular Value Decomposition (SVD) within a geometrically constrained subspace while freezing the residual components. This method preserves the pre-trained geometric structure and enables efficient GPU computation through dense operators. Experiments on Qwen and Llama demonstrate that GeoRA mitigates optimization bottlenecks caused by geometric misalignment. It consistently outperforms established low-rank baselines on key mathematical benchmarks, achieving state-of-the-art (SOTA) results. Moreover, GeoRA shows superior generalization and resilience to catastrophic forgetting in out-of-domain tasks.

Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments

Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user's intents and dynamically adapt to evolving external environments. In this paper, we propose a novel interaction paradigm for proactive Task-oriented Agents capable of bridging the gap between relatively static user's needs and a dynamic environment. We formalize proactivity through two key capabilities, (i) Intent-Conditioned Monitoring: The agent autonomously formulates trigger conditions based on dialog history; (ii) Event-Triggered Follow-up: The agent actively engages the user upon detecting useful environmental updates. We introduce a high-quality data synthesis pipeline to construct complex, multi-turn dialog data in a dynamic environment. Furthermore, we attempt to address the lack of evaluation criteria of task-oriented interaction in a dynamic environment by proposing a new benchmark, namely ChronosBench. We evaluated some leading close-source and open-source models at present and revealed their flaws in long-term task-oriented interaction. Furthermore, our fine-tuned model trained using synthetic data for supervised learning achieves a task completion rate of 85.19% for complex tasks including shifts in user intent, outperforming other models under test. And the result validated the effectiveness of our data-driven strategy.

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models

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.

UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods exhibit two issues. They rely on static and context-unaware profiles, necessitating extensive manual redesign for new scenarios, thus limiting generalizability. Moreover, they neglect human strategic thinking, leading to vulnerability to agent manipulation. To address these issues, we propose UserLM-R1, a novel user language model with reasoning capability. Specifically, we first construct comprehensive user profiles with both static roles and dynamic scenario-specific goals for adaptation to diverse scenarios. Then, we propose a goal-driven decision-making policy to generate high-quality rationales before producing responses, and further refine the reasoning and improve strategic capabilities with supervised fine-tuning and multi-reward reinforcement learning. Extensive experimental results demonstrate that UserLM-R1 outperforms competitive baselines, particularly on the more challenging adversarial set.

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management

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.

Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering

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. The code will be released soon.

Rotation-Robust Regression with Convolutional Model Trees

We study rotation-robust learning for image inputs using Convolutional Model Trees (CMTs) [1], whose split and leaf coefficients can be structured on the image grid and transformed geometrically at deployment time. In a controlled MNIST setting with a rotation-invariant regression target, we introduce three geometry-aware inductive biases for split directions -- convolutional smoothing, a tilt dominance constraint, and importance-based pruning -- and quantify their impact on robustness under in-plane rotations. We further evaluate a deployment-time orientation search that selects a discrete rotation maximizing a forest-level confidence proxy without updating model parameters. Orientation search improves robustness under severe rotations but can be harmful near the canonical orientation when confidence is misaligned with correctness. Finally, we observe consistent trends on MNIST digit recognition implemented as one-vs-rest regression, highlighting both the promise and limitations of confidence-based orientation selection for model-tree ensembles.

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) reasoning improves accuracy but incurs prohibitive latency for real-time query correction. A potential solution is to output an answer before reasoning to reduce latency; however, under autoregressive decoding, the early answer is independent of subsequent reasoning, preventing the model from leveraging its reasoning capability to improve accuracy. To address this issue, we propose Sandwich Reasoning (SandwichR), a novel approach that explicitly aligns a fast initial answer with post-hoc reasoning, enabling low-latency query correction without sacrificing reasoning-aware accuracy. SandwichR follows an Answer-Reasoning-Answer paradigm, producing an initial correction, an explicit reasoning process, and a final refined correction. To align the initial answer with post-reasoning insights, we design a consistency-aware reinforcement learning (RL) strategy: a dedicated consistency reward enforces alignment between the initial and final corrections, while margin-based rejection sampling prioritizes borderline samples where reasoning drives the most impactful corrective gains. Additionally, we construct a high-quality query correction dataset, addressing the lack of specialized benchmarks for complex query correction. Experimental results demonstrate that SandwichR achieves SOTA accuracy comparable to standard CoT while delivering a 40-70% latency reduction, resolving the latency-accuracy trade-off in online search.