Xuan Jiang

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.

Ride-hailing platforms face the challenge of balancing passenger waiting times with overall system efficiency under highly uncertain supply-demand conditions. Adaptive delayed matching, which controls the holding intervals for batched sets of requests and vehicles, reveals an inherent trade-off between matching and pickup delays. The resulting environment with temporally varying request arrival patterns and dynamic congestion calls for more expressive networks with sufficient capacity to capture their non-stationarity. To address the limitations of existing methods that rely on shallow encoders that cannot capture dynamic supply-demand patterns and congestion effects, we introduce the Regime-Aware Spatio-Temporal Mixture-of-Experts (RAST-MoE) framework, which formalizes adaptive delayed matching as a regime-aware Markov Decision Process and equips RL agents with a self-attention MoE encoder. Instead of relying on a single monolithic network, our design allows different experts to specialize automatically in varying operational conditions, improving representation capacity while maintaining per-sample computation efficiency. Despite its modest size of only 12M parameters, our framework consistently outperforms strong baselines. On real-world Uber trajectory data from San Francisco, it reduces average matching delay by 10%, and pickup delay by 15%. In addition, it demonstrates robustness to unseen demand regimes, stable training behavior without reward hacking, and expert specialization to different regimes. This study shows the strength of MoE-enhanced RL for large-scale decision-making tasks with complex spatiotemporal dynamics.

Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fragile. Methods such as DenseMixer and ESFT mitigate router collapse with dense mixing or auxiliary load-balancing losses, but these introduce noisy gradients that often degrade performance. In preliminary experiments, we systematically pruned experts and observed that while certain super experts are activated far more frequently, discarding less used experts still leads to notable performance degradation. This suggests that even rarely activated experts encode non-trivial knowledge useful for downstream tasks. Motivated by this, we propose an auxiliary-loss-free MoE SFT framework that combines bias-driven sparsification with always-active gated condenser experts. Rather than enforcing balanced activation across all experts, our method encourages task-relevant experts to remain active while pushing long-tailed experts toward inactivity. The condenser experts provide a persistent, learnable pathway that alleviates gradient starvation and facilitates consolidation of information that would otherwise remain fragmented across sparsely activated experts. Analysis further suggest that this design better preserves long-tailed expert information under sparse routing. Experiments on large-scale MoE models demonstrate that our approach outperforms state-of-the-art SFT baselines such as DenseMixer and ESFT, achieving average gain of 2.5%+ on both mathematical reasoning and commonsenseQA benchmarks.

Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment challenges. Prior MoE compression approaches catastrophically fail when evaluated on general-purpose benchmarks beyond commonsense reasoning. We trace this failure to the granularity of compression: important capabilities are distributed across experts but concentrated in FFN sparse intermediate dimensions. To identify these dimensions, we use Fisher importance which outperforms activation-, router-score-, and magnitude-based alternatives, and identifies tiny sets of task-critical dimensions: in Qwen1.5-MoE, removing as few as 12 of 1.35M routed-FFN intermediate dimensions collapses GSM8K accuracy while largely preserving factual-knowledge performance. Building on this, we propose Fisher-MoE, which operates within FFN to remove intermediate dimensions ranked by Fisher importance. At the same 50% MoE compression ratio, Fisher-MoE preserves model capability, while reducing weight memory by ~45% and improving inference throughput by 21%. These findings suggest intermediate dimension granularity is an effective unit for both compression and ranking where capability concentrates in MoE models.

Anomaly detection in cloud sites remains a critical yet challenging task. Existing approaches that rely solely on metric data often suffer from high false positive rates (FPR) due to data imbalance between normal and anomalous events, leading to significant operational overhead for system reliance engineers. Recent advances in large language models (LLMs) offer new opportunities for integrating metrics with log data, enabling more accurate and interpretable anomaly detection. In this paper, we propose CloudAnoAgent, the first neuro-symbolic LLM-based agent for anomaly detection in cloud environments. CloudAnoAgent jointly processes structured metrics and textual log data in a unified pipeline, leveraging symbolic verification to validate detection hypotheses and generate structured anomaly reports. To support systematic evaluation, we introduce CloudAnoBench, the first benchmark that provides LLM-generated paired metrics and log data with fine-grained anomaly behavior annotations, filling a critical gap in existing datasets. Experimental results demonstrate that CloudAnoAgent improves anomaly classification accuracy by 46.36% and 36.67% on average and reduces the FPR by 36.67% and 33.89% on average over traditional baselines and LLM-only baseline, with a boost on anomaly type detection accuracy by 12.8% compared to vanilla LLM prompting. These results demonstrate the strengths of our approach in improving detection accuracy, reducing false positives, and enhancing interpretability, thereby supporting practical deployment in enterprise cloud environments.

Video benchmarks ask what happens in a video. Socially responsive systems also need to relate what a person watches to how that person responds: a laugh follows a visual gag; a pause matters only against the same viewer’s surrounding behavior. ReactionBench asks whether current multimodal models can rank, temporally match, and explain a viewer’s reaction against the stimulus it was watching. Across seven models, the answer is: not yet.

LoRA and its variants have become popular parameter-efficient fine-tuning (PEFT) methods due to their ability to avoid excessive computational costs. However, an accuracy gap often exists between PEFT methods and full fine-tuning (FT), and this gap has yet to be systematically studied. In this work, we introduce a method for selecting sparse sub-matrices that aim to minimize the performance gap between PEFT vs. full fine-tuning (FT) while also reducing both fine-tuning computational cost and memory cost. Our Sparse Matrix Tuning (SMT) method begins by identifying the most significant sub-matrices in the gradient update, updating only these blocks during the fine-tuning process. In our experiments, we demonstrate that SMT consistently surpasses other PEFT baseline (e.g. LoRA and DoRA) in fine-tuning popular large language models such as LLaMA across a broad spectrum of tasks, while reducing the GPU memory footprint by 67% compared to FT. We also examine how the performance of LoRA and DoRA tends to plateau and decline as the number of trainable parameters increases, in contrast, our SMT method does not suffer from such issue.

Traffic propagation simulation is crucial for urban planning, enabling congestion analysis, travel time estimation, and route optimization. Traditional micro-simulation frameworks are limited to main roads due to the complexity of urban mobility and large-scale data. We introduce the Large Scale Multi-GPU Parallel Computing based Regional Scale Traffic Simulation Framework (LPSim), a scalable tool that leverages GPU parallel computing to simulate extensive traffic networks with high fidelity and reduced computation time. LPSim performs millions of vehicle dynamics simulations simultaneously, outperforming CPU-based methods. It can complete simulations of 2.82 million trips in 6.28 minutes using a single GPU, and 9.01 million trips in 21.16 minutes on dual GPUs. LPSim is also tested on dual NVIDIA A100 GPUs, achieving simulations about 113 times faster than traditional CPU methods. This demonstrates its scalability and efficiency for large-scale applications, making LPSim a valuable resource for researchers and planners. Code: https://github.com/Xuan-1998/LPSim