arXiv subjects

Alexey Malakhov

Publications and source records attributed to Alexey Malakhov.

5 recordsLinked to original sources

arXiv2026

ESSA: Evolutionary Strategies for Scalable Alignment

Online alignment of large language models (LLMs) is dominated by reinforcement learning from human feedback (RLHF) with gradient-based optimizers such as PPO or GRPO. While effective, these pipelines require backpropagation through long rollouts, gradient synchronization across devices, and careful hyperparameter tuning, all of which become increasingly costly at scale. We present ESSA (Evolutionary Strategies for Scalable Alignment), a gradient-free online alignment stage that follows supervised fine-tuning (SFT) and replaces the gradient loop with inference-only black-box search. ESSA optimizes only the singular values of low-rank adaptation (LoRA) factors after a short SFT warm-start, restricting the search to a compact, task-aligned subspace where evolutionary search is practical even for 72B-parameter models. Because the loop is inference-only, ESSA is compatible with INT4/INT8 weight quantization and reduces inter-GPU communication to a few bytes per iteration. Across instruction following (IFEval), preference-based assistant tuning (HelpSteer2, HH-RLHF), and mathematical reasoning (GSM8K, MATH500), ESSA matches or exceeds LoRA-GRPO in the reported LoRA comparisons; on GSM8K it also outperforms Online DPO and PPO, while remaining competitive with both methods on IFEval. At scale, ESSA reaches a fixed MATH500 accuracy on Qwen2.5-32B/PRM800K up to 7.8x faster than LoRA-GRPO on 128 GPUs.

cs.LG↗

arXiv2026

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with finite rollout sets that can reinforce only the correct behavior they expose. At practical group sizes, updates can miss rare-correct trajectories while still containing mixed rewards, concentrating probability on more common sampled solutions. We derive the probability of such prompt-local tail-miss events as a function of group size, showing non-monotonic behavior, and in the categorical abstraction characterize how unsampled-correct mass can shrink even as total correct mass grows. Motivated by this analysis, we propose a difficulty-aware scaling coefficient, inspired by Focal loss, that down-weights updates on high-success sampled groups. Empirically, categorical simulation illustrates the same effect in the categorical setting, Maze provides a single-solution test, and LLM experiments include a representative GRPO group-size sweep together with fixed-$N$ transfer across GRPO, DAPO, and CISPO. On Qwen2.5-7B at $N{=}8$, our method improves average math pass@256 from 64.1 $\rightarrow$ 70.3 (GRPO), 69.3 $\rightarrow$ 72.5 (DAPO), and 73.2 $\rightarrow$ 76.8 (CISPO); OOD pass@256 also improves in all three cases, without increasing group size or computational cost.

cs.LG↗

arXiv2026

Trust-Region Behavior Blending for On-Policy Distillation

On-policy distillation (OPD) trains a student on prefixes sampled from its own policy while matching a stronger teacher. This addresses the prefix mismatch of offline distillation, but early student rollouts can still be poor, placing teacher supervision on weak or low-quality prefixes. We propose Trust-Region behavior Blending (TRB), a warmup method that replaces the early rollout policy with the closest-to-teacher behavior policy inside a student-centered KL trust region, while keeping the per-prefix reverse-KL OPD loss unchanged. The KL budget is annealed to zero, so training returns to pure student rollouts after warmup. Across two math-reasoning distillation settings, TRB attains the strongest average among the compared methods.

cs.LG↗

arXiv2026

The Differences Between Direct Alignment Algorithms are a Blur

Direct Alignment Algorithms (DAAs) simplify LLM alignment by directly optimizing policies, bypassing reward modeling and RL. While DAAs differ in their use of SFT (one-stage vs. two-stage) and the scalar score they optimize (likelihood vs. odds ratios), the key performance drivers remain underexplored. We present a systematic comparison and analyze a previously overlooked axis - the ranking objective (pairwise vs. pointwise). To isolate this factor, we propose a unified training framework across DAAs by (i) converting one-stage methods (ORPO, ASFT) into a two-stage pipeline with an explicit SFT phase and (ii) introducing a $β$ parameter that places all methods in the same hyperparameter space and improves the quality of odds-ratio DAAs (ORPO, ASFT). Under this setup, the ranking objective emerges as the primary determinant of alignment quality, whereas the particular scalar score (policy-reference ratio vs. odds ratio) is secondary. We corroborate this on instruction-following tasks and further confirm it on math-reasoning benchmarks across model scales. Evidence suggests that this stems from how these objectives interact with prompt-specific biases, supported both by strictly controlled experiments and by observations on real data. Our findings underscore the need for nuanced evaluations in DAA research to avoid oversimplified claims of superiority.

cs.LG↗

arXiv2025

Learn Your Reference Model for Real Good Alignment

Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the reference policy, leading to a decrease in sample quality. We propose a new paradigm of offline alignment methods, called Trust Region (including variants TR-DPO, TR-IPO, TR-KTO), which dynamically updates the reference policy throughout the training process. Our results show that TR alignment methods effectively mitigate overoptimization, enabling models to maintain strong performance even when substantially deviating from the initial reference policy. We demonstrate the efficacy of these approaches not only through toy examples that exhibit reduced overoptimization, but also through direct, side-by-side comparisons in specific tasks such as helpful and harmless dialogue, as well as summarization, where they surpass conventional methods. Additionally, we report significant improvements in general-purpose assistant setups with the Llama3 model on the AlpacaEval 2 and Arena-Hard benchmarks, highlighting the advantages of Trust Region methods over classical approaches.

cs.LG↗