Searcharxiv⌕ Search

arXiv subjects

Yingbin Liang

Publications and source records attributed to Yingbin Liang.

At least 19 recordsLinked to original sources
arXiv2026

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server. However, most existing DBO methods rely on lower-level strong convexity (LLSC) to guarantee unique solutions and a well-defined hypergradient for stationarity measure, hindering their applicability in many practical scenarios not satisfying LLSC. To overcome this limitation, we introduce a new single-loop DBO algorithm called diminishing quadratically-regularized bilevel decentralized optimization (DUET), which eliminates the need for LLSC by introducing a diminishing quadratic regularization to the lower-level (LL) objective. We show that DUET achieves an iteration complexity of $O(1/T^{1-5p-\frac{11}{4}\tau})$ for approximate KKT-stationary point convergence under relaxed assumptions, where $p$ and $\tau $ are control parameters for LL learning rate and averaging, respectively. In addition, our DUET algorithm incorporates gradient tracking to address data heterogeneity, a key challenge in DBO settings. To the best of our knowledge, this is the first work to tackle DBO without LLSC under decentralized settings with data heterogeneity. Numerical experiments validate the theoretical findings and demonstrate the practical effectiveness of our proposed algorithms.

math.OC↗
arXiv2026

PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents

Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is challenging, as reinforcement learning often suffers from sparse rewards and weak credit assignment despite matching the prompt-only inference setting, while supervised fine-tuning on expert traces provides dense process supervision but can over-constrain the model to fixed trajectories. To tackle this, we propose PACT, a Privileged trAce Co-Training framework for multi-turn tool-use agents. The key idea is to use expert traces only as training-time optimization signals rather than rollout-time hints. PACT keeps rollout generation prompt-only, then uses expert traces to guide optimization through two complementary signals: a trace-conditioned RL surrogate that evaluates prompt-only rollouts under expert-trace context, and a component-aware SFT loss that supervises reasoning prefixes and tool-calls with annealed strength. To reduce over-reliance on the training-only trace context, PACT further introduces a prompt-only anchoring. We also provide a latent-trace view that connects the two trace-based objectives and explains how expert traces can guide optimization without being used during rollout generation. Experiments on FTRL, BFCL, and ToolHop show that PACT consistently improves over strong SFT- and RL-based baselines, highlighting the value of privileged trace co-training for multi-turn tool-use learning.

cs.CL↗
arXiv2026

Agentic Transformers Provably Learn to Search via Reinforcement Learning

Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a stochastic $k$-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct a two-head transformer that implements randomized depth-first search (DFS): one head tracks previous actions, while the other detects failure outcomes and triggers backtracking. We then analyze the training dynamics of policy gradient under a depth-wise curriculum, showing that this same DFS mechanism emerges in stages from sparse reinforcement feedback without expert demonstrations. The resulting policy exhibits depth generalization: after training only on depth-$1$ and depth-$2$ trees, it succeeds on deeper full trees. We further show that, under imbalanced goal distributions, discounting the return leads to a ranked DFS policy that prioritizes higher-probability branches. Overall, our results identify a mechanistic normal form for transformer-based search, in which attention heads specialize and cooperate to extract decision-relevant traces from context and convert them into agentic action selection via RL training.

cs.LG↗
arXiv2026

From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow mixing. In this work, we propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD). GADD leverages the structure of the concrete score function to construct Gibbs posterior likelihoods directly, without requiring any additional training beyond standard score estimation. We show that GADD achieves an overall sampling complexity of $\mathcal{O}(\mathrm{polylog} (\varepsilon^{-1}))$, yielding the first such rate for diffusion-based samplers for uniform-rate discrete diffusion models. We also conduct numerical experiments demonstrating the practical advantages of GADD across synthetic data, zero-shot text sampling, and zero-shot conditional music generation. These results corroborate the theory and show that GADD consistently improves sample quality and wall-clock efficiency over standard baselines, including vanilla Euler methods and CTMC correctors. Beyond this, our theoretical analysis introduces a novel framework for analyzing predictor-corrector methods in discrete diffusion models, which may be of independent interest. Unlike existing approaches that rely on the Girsanov change-of-measure technique, our method is based on an induction argument that tracks error propagation across predictor iterations while accounting for inaccuracies in the corrector updates.

cs.LG↗
arXiv2026

Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL algorithms achieve favorable sample complexity, but often rely on computationally intractable oracles. In this paper, we use supervised learning as a computational proxy to establish a clear hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs). This hierarchy shows that policy evaluation is the most computationally efficient oracle, provided that supervised learning can be efficiently solved. Motivated by this observation, we propose a novel optimistic actor-critic algorithm that relies solely on the policy evaluation oracle. We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works. We further extend our theoretical results to approximately low-rank MDPs and demonstrate that this setting captures a broad class of real-world environments. Finally, we validate our theoretical results with experiments on several standard Gym environments.

cs.LG↗
arXiv2026

Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences

Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth objective. In practical RLHF systems, however, feedback is typically \emph{multi-source} (annotators, experts, reward models, heuristics) and can exhibit systematic, persistent mismatches due to subjectivity, expertise variation, and annotation/modeling artifacts. We study episodic RL from \emph{multi-source imperfect preferences} through a cumulative imperfection budget: for each source, the total deviation of its preference probabilities from an ideal oracle is at most $\omega$ over $K$ episodes. We propose a unified algorithm with regret $\tilde{O}(\sqrt{K/M}+\omega)$, which exhibits a best-of-both-regimes behavior: it achieves $M$-dependent statistical gains when imperfection is small (where $M$ is the number of sources), while remaining robust with unavoidable additive dependence on $\omega$ when imperfection is large. We complement this with a lower bound $\tilde{\Omega}(\max\{\sqrt{K/M},\omega\})$, which captures the best possible improvement with respect to $M$ and the unavoidable dependence on $\omega$, and a counterexample showing that na\"ively treating imperfect feedback as oracle-consistent can incur regret as large as $\tilde{\Omega}(\min\{\omega\sqrt{K},K\})$. Technically, our approach involves imperfection-adaptive weighted comparison learning, value-targeted transition estimation to control hidden feedback-induced distribution shift, and sub-importance sampling to keep the weighted objectives analyzable, yielding regret guarantees that quantify when multi-source feedback provably improves RLHF and how cumulative imperfection fundamentally limits it.

cs.LG↗
arXiv2026

HIPO: Instruction Hierarchy via Constrained Reinforcement Learning

Hierarchical Instruction Following (HIF) refers to the problem of prompting large language models with a priority-ordered stack of instructions. Standard methods like RLHF and DPO typically fail in this problem since they mainly optimize for a single objective, failing to explicitly enforce system prompt compliance. Meanwhile, supervised fine-tuning relies on mimicking filtered, compliant data, which fails to establish the priority asymmetry at the algorithmic level. In this paper, we introduce \textsc{HIPO}, a novel alignment framework that formulates HIF as a Constrained Markov Decision Process. \textsc{HIPO} elevates system prompts from mere input context to strict algorithmic boundaries. Using a primal-dual safe reinforcement learning approach, the algorithm dynamically enforces system prompt compliance as an explicit constraint, maximizing user utility strictly within this feasible region. Extensive evaluations across diverse model architectures (e.g., Qwen, Phi, Llama) demonstrate that \textsc{HIPO} significantly improves both system compliance and user utility. Furthermore, mechanistic analysis reveals that this constrained optimization autonomously drives the model to shift its attention toward long-range system tokens, providing a principled foundation for reliable LLM deployment in complex workflows.

cs.LG↗
arXiv2026

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the existing theory yields guarantees essentially comparable to those of SGD, leaving the empirical performance gap insufficiently explained. In this paper, we uncover a key second-moment normalization in Adam and develop a stopping-time/martingale analysis that provably distinguishes Adam from SGD under the classical bounded variance model (a second moment assumption). In particular, we establish the first theoretical separation between the high-probability convergence behaviors of the two methods: Adam achieves a $\delta^{-1/2}$ dependence on the confidence parameter $\delta$, whereas corresponding high-probability guarantee for SGD necessarily incurs at least a $\delta^{-1}$ dependence.

cs.LG↗
arXiv2026

Sharp Convergence Rates for Masked Diffusion Models

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging as competitive alternatives to autoregressive models. Among existing samplers, the Euler method remains the standard choice in many applications, and more recently, the First-Hitting Sampler (FHS) has shown considerable promise for masked diffusion models. Despite their practical success, the theoretical understanding of these samplers remains limited. Existing analyses are conducted in Kullback-Leibler (KL) divergence, which often yields loose parameter dependencies and requires strong assumptions on score estimation. Moreover, these guarantees do not cover recently developed high-performance sampler of FHS. In this work, we first develop a direct total-variation (TV) based analysis for the Euler method that overcomes these limitations. Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees without requiring any surrogate initialization. Also for this setting, we provide the first convergence lower bound for the Euler sampler, establishing tightness with respect to both the data dimension $d$ and the target accuracy $\varepsilon$. Finally, we analyze the FHS sampler and show that it incurs no sampling error beyond that induced by score estimation, which we show to be tight with a matching lower error bound. Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS, which may be of independent interest.

cs.LG↗
arXiv2026

On the Emergence of Implicit Curriculum in RLVR Learning Dynamics

Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier to extended reasoning. To understand this, we develop a theory of the training dynamics of RLVR for transformers on compositional reasoning tasks. Our theory shows that mixed-difficulty training naturally induces an implicit curriculum: without any explicit schedule, easier problems become learnable first and shape the frontier for harder ones, creating a learning progression from easy to hard during optimization. The effectiveness of this curriculum is governed by the smoothness of the difficulty spectrum. When the spectrum is smooth, training dynamics enter a well-behaved relay regime, in which persistent gradient signals on easier problems make slightly harder ones tractable and keep training at the edge of competence. When the spectrum contains abrupt discontinuities, training undergoes grokking-type phase transitions with prolonged plateaus before progress recurs. As a technical contribution, our analysis develops and adapts techniques from Fourier analysis on finite groups to our setting. We validate the predicted mechanisms empirically via controlled synthetic experiments and real-model RLVR runs.

cs.LG↗
arXiv2026

Constraint-Rectified Training for Efficient Chain-of-Thought

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking. Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy, either through length-aware reward design or prompt-based calibration. However, these heuristic-based approaches may suffer from severe accuracy drop and be very sensitive to hyperparameters. To address these problems, we introduce CRT (Constraint-Rectified Training), a principled post-training framework based on reference-guarded constrained optimization, yielding a more stable and interpretable formulation for efficient reasoning. CRT alternates between minimizing reasoning length and rectifying accuracy only when performance falls below the reference, enabling stable and effective pruning of redundant reasoning. We further extend CRT with a two-stage training scheme that first discovers the shortest reliable reasoning patterns and then refines accuracy under a learnt length budget, preventing the re-emergence of verbose CoT. Our comprehensive evaluation shows that this framework consistently reduces token usage while maintaining answer quality at a robust and reliable level. Further analysis reveals that CRT improves reasoning efficiency not only by shortening responses but also by reducing internal language redundancy, leading to a new evaluation metric. Moreover, CRT-based training naturally yields a sequence of intermediate checkpoints that span a spectrum of explanation lengths while preserving correctness, enabling fine-grained control over reasoning verbosity without retraining.

cs.LG↗
arXiv2026

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is fundamentally governed by reward design. Despite its importance, the relationship between reward modeling and core LLM challenges--such as evaluation bias, hallucination, distribution shift, and efficient learning--remains poorly understood. This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment, shaping what models learn, how they generalize, and whether their outputs can be trusted. We introduce Reasoning-Aligned Reinforcement Learning (RARL), a reasoning-centric taxonomic perspective that organizes diverse reward paradigms for multi-step reasoning. Within this perspective, we present a taxonomy of reward mechanisms, analyze reward hacking as a pervasive failure mode, and examine how reward signals unify challenges ranging from inference-time scaling to hallucination mitigation. We further critically evaluate existing benchmarks, highlighting vulnerabilities such as data contamination and reward misalignment, and outline directions for more robust evaluation. By integrating fragmented research threads and clarifying the interplay between reward design and fundamental reasoning capabilities, this work provides a foundational roadmap for building reasoning models that are robust, verifiable, and trustworthy.

cs.LG↗
arXiv2026

Learnable Chernoff Baselines for Inference-Time Alignment

We study inference-time reward-guided alignment for generative models. Existing methods often rely on either architecture-specific adaptations or computationally costly inference procedures. We introduce Learnable Chernoff Baselines (LCBs) as a method for efficiently and approximately sampling from the exponentially tilted kernels that arise from KL-regularized reward alignment. Using only black-box sampling access to the pretrained model, LCBs implement a form of rejection sampling with adaptively selected acceptance probabilities, which allows fine-grained control over inference-compute scaling. We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling while using substantially fewer queries to the pretrained model.

cs.LG↗
arXiv2026

Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation

Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as multi-turn code generation. While online RL tends to perform better than offline RL, its higher training cost and instability hinders wide adoption. In this paper, we build on the observation that multi-turn code generation can be formulated as a one-step recoverable Markov decision process and propose contextual bandit learning with offline trajectories (Cobalt), a new method that combines the benefits of online and offline RL. Cobalt first collects code generation trajectories using a reference LLM and divides them into partial trajectories as contextual prompts. Then, during online bandit learning, the LLM is trained to complete each partial trajectory prompt through single-step code generation. Cobalt outperforms two multi-turn online RL baselines based on GRPO and VeRPO, and substantially improves R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 absolute Pass@1 scores on LiveCodeBench. Also, we analyze LLMs' in-context reward hacking behaviors and augment Cobalt training with perturbed trajectories to mitigate this issue. Overall, our results demonstrate Cobalt as a promising solution for iterative decision-making tasks like multi-turn code generation. Our code and data are available at https://github.com/OSU-NLP-Group/cobalt.

cs.LG↗
arXiv2026

ConvexBench: Can LLMs Recognize Convex Functions?

Convex analysis is a modern branch of mathematics with many applications. As Large Language Models (LLMs) start to automate research-level math and sciences, it is important for LLMs to demonstrate the ability to understand and reason with convexity. We introduce \cb, a scalable and mechanically verifiable benchmark for testing \textit{whether LLMs can identify the convexity of a symbolic objective under deep functional composition.} Experiments on frontier LLMs reveal a sharp compositional reasoning gap: performance degrades rapidly with increasing depth, dropping from an F1-score of $1.0$ at depth $2$ to approximately $0.2$ at depth $100$. Inspection of models' reasoning traces indicates two failure modes: \textit{parsing failure} and \textit{lazy reasoning}. To address these limitations, we propose an agentic divide-and-conquer framework that (i) offloads parsing to an external tool to construct an abstract syntax tree (AST) and (ii) enforces recursive reasoning over each intermediate sub-expression with focused context. This framework reliably mitigates deep-composition failures, achieving substantial performance improvement at large depths (e.g., F1-Score $= 1.0$ at depth $100$).

cs.AI↗
arXiv2025

Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems

Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers (MoT), a tractable theoretical framework in which each transformer block acts as an expert governed by a continuously trained gating network. This design allows us to isolate and study the core learning dynamics of expert specialization and attention alignment. In particular, we develop a three-stage training algorithm with continuous training of the gating network, and show that each transformer expert specializes in a distinct class of tasks and that the gating network accurately routes data samples to the correct expert. Our analysis shows how expert specialization reduces gradient conflicts and makes each subtask strongly convex. We prove that the training drives the expected prediction loss to near zero in $O(\log(\epsilon^{-1}))$ iteration steps, significantly improving over the $O(\epsilon^{-1})$ rate for a single transformer. We further validate our theoretical findings through extensive real-data experiments, demonstrating the practical effectiveness of MoT. Together, these results offer the first unified theoretical account of transformer-level specialization and learning dynamics, providing practical guidance for designing efficient large-scale models.

cs.LG↗
arXiv2025

Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information

Uncovering hidden graph structures underlying real-world data is a critical challenge with broad applications across scientific domains. Recently, transformer-based models leveraging the attention mechanism have demonstrated strong empirical success in capturing complex dependencies within graphs. However, the theoretical understanding of their training dynamics has been limited to tree-like graphs, where each node depends on a single parent. Extending provable guarantees to more general directed acyclic graphs (DAGs) -- which involve multiple parents per node -- remains challenging, primarily due to the difficulty in designing training objectives that enable different attention heads to separately learn multiple different parent relationships. In this work, we address this problem by introducing a novel information-theoretic metric: the kernel-guided mutual information (KG-MI), based on the $f$-divergence. Our objective combines KG-MI with a multi-head attention framework, where each head is associated with a distinct marginal transition kernel to model diverse parent-child dependencies effectively. We prove that, given sequences generated by a $K$-parent DAG, training a single-layer, multi-head transformer via gradient ascent converges to the global optimum in polynomial time. Furthermore, we characterize the attention score patterns at convergence. In addition, when particularizing the $f$-divergence to the KL divergence, the learned attention scores accurately reflect the ground-truth adjacency matrix, thereby provably recovering the underlying graph structure. Experimental results validate our theoretical findings.

cs.LG↗
arXiv2025

Monitoring State Transitions in Markovian Systems with Sampling Cost

We consider a node-monitor pair, where the node's state varies with time. The monitor needs to track the node's state at all times; however, there is a fixed cost for each state query. So the monitor may instead predict the state using time-series forecasting methods, including time-series foundation models (TSFMs), and query only when prediction uncertainty is high. Since query decisions influence prediction accuracy, determining when to query is nontrivial. A natural approach is a greedy policy that predicts when the expected prediction loss is below the query cost and queries otherwise. We analyze this policy in a Markovian setting, where the optimal (OPT) strategy is a state-dependent threshold policy minimizing the time-averaged sum of query cost and prediction losses. We show that, in general, the greedy policy is suboptimal and can have an unbounded competitive ratio, but under common conditions such as identically distributed transition probabilities, it performs close to OPT. For the case of unknown transition probabilities, we further propose a projected stochastic gradient descent (PSGD)-based learning variant of the greedy policy, which achieves a favorable predict-query tradeoff with improved computational efficiency compared to OPT.

cs.LG↗