S

Shengcai Liu

Total Citations
937
h-index
15
Papers
4

Publications

#1 2608.02391v1 Aug 03, 2026

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-efficient full-parameter post-training without backpropagation and can eventually match the performance of gradient-based reinforcement learning (RL). However, resource-constrained settings typically offer only a few GPUs, so the high GPU-hour requirements of ES translate into prohibitively long training times. To address this, we introduce Cooperative Parameter-subspace Evolution Strategy (CoPES), a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency. We post-train a Qwen3.5-4B tool-using agent for the math task and evaluate it on five benchmarks of varying difficulty. Under the GPU-hour budget of full-parameter GRPO's best validation checkpoint, CoPES recovers 92% of GRPO's validation-accuracy gain, versus 67% for standard ES, while its theoretical GPU memory requirement is less than one-eighth that of full-parameter GRPO. It consistently outperforms standard ES and LoRA-based GRPO on all evaluated pass@k metrics across the five benchmarks. Additional experiments further show the advantage of CoPES on the question-answering task. These results demonstrate an improved trade-off between memory requirements and training time for agentic LLM post-training under resource constraints. The code is open-sourced in https://github.com/MetaronWang/CoPES

Ning Lu Ke Tang Shengcai Liu Jiahao Wu Zhiyuan Wang +3
0 Citations
#2 2607.27807v1 Jul 30, 2026

Learning-Augmented and Randomized Algorithms for Line Aggregation with Delays

This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested service lengths, and evaluate the algorithms in terms of robustness and consistency. For each $λ\in (0,1]$, we first propose a deterministic learning-augmented \textsc{Balance} algorithm that is $(4/λ+1/λ^2)$-robust and $(4+λ)$-consistent. We also propose a randomized algorithm for the problem in the classical adversarial model, which is $(e+1)$-competitive against an oblivious adversary, improving over the deterministic $5$-competitive \textsc{Balance} benchmark~\cite{bienkowski2013chain}. Notably, this competitive ratio is even lower than the lower bound of $4$ for deterministic online algorithms. Moreover, we establish a lower bound of $e$ on the competitive ratio of randomized online algorithms, improving the previous lower bound of $e/(e-1)$. Besides, we combine the two ideas and obtain a randomized learning-augmented algorithm that is $(e/λ+1/λ^2)$-robust and $(e+λ)$-consistent. Finally, we conduct numerical experiments to complement our theoretical analysis and evaluate the empirical performance of our algorithms.

Ke Tang Shengcai Liu Tianhan Lu Runtian Ren
0 Citations
#3 2603.25184v1 Mar 26, 2026

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility. To address this problem, we investigate how to select high-utility prompts before the rollout phase. Our experimental analysis reveals that sample utility is non-uniform and evolving: the strongest learning signals concentrate at the ``learning edge", the intersection of intermediate difficulty and high uncertainty, which shifts as training proceeds. Motivated by this, we propose HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL. HIVE utilizes historical reward trajectories for coarse selection and employs prompt entropy as a real-time proxy to prune instances with stale utility. By evaluating HIVE across multiple math reasoning benchmarks and models, we show that HIVE yields significant rollout efficiency without compromising performance.

Kun Wang Ning Lu Yanting Yang Li Qing Ke Tang +4
2 Citations
#4 2602.00488v3 Jan 31, 2026

OD-Gear: Online Decomposition and Group Sampling for Expert-Guided Adversarial Routing in Scalable Capacitated Vehicle Routing

Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generalization of neural solvers. To bridge this gap, we propose OD-Gear, an expert-guided adversarial framework that integrates hybrid genetic search (HGS) and online barycenter clustering (BCC) decomposition with group-relative optimization. OD-Gear internalizes expert heuristics into a graph attention network (GAT)-based policy via high-fidelity knowledge distillation. Our minimax adversarial training distills divide-and-conquer strategies into dense surrogate rewards, while a group-sampling strategy exploits relative solution advantages to promote both diversity and quality. This architecture enables high-quality, clustering-free inference on massive graphs, effectively bypassing the overhead of traditional decomposition. Empirical results demonstrate that OD-Gear achieves state-of-the-art (SOTA) performance across most benchmarks, remaining highly competitive at the 10,000-node scale. By providing heuristic-quality solutions with low-latency, OD-Gear offers a robust and scalable framework for large-scale CVRP.

Zisheng Chen Shengcai Liu Dongbin Jiao Xianyi Wang Jintao Shi +1
0 Citations