Search arXiv⌕ Search

arXiv subjects

Ya-Qin Zhang

Publications and source records attributed to Ya-Qin Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. Yet long-horizon autoregressive rollouts introduce a fundamental limitation: local policy mismatch can compound into severe state distribution shift over trajectories. Existing LLM RL methods, such as GRPO and GSPO, control policy mismatch at the token or sequence level, but overlook this trajectory-induced shift, causing training instability and eventual collapse as the horizon grows. To close the state distribution gap, we propose Trajectory-Aware Policy Optimization (TAPO), a principled framework that theoretically derives the state-distribution correction from the off-policy policy gradient and incorporates it into the RL objective. TAPO further employs a geometric-mean estimator for variance reduction, together with a length-aware dynamic clipping that prevents overly deviated updates across the trajectory. Extensive experiments demonstrate that TAPO significantly surpasses existing LLM RL algorithms across eight competition-level benchmarks, achieving up to 48% and 12% improvement over GRPO on mathematical reasoning and algorithmic coding, with substantially enhanced training stability.

cs.LG↗
arXiv2026

Coder as Editor: Code-driven Interpretable Molecular Editing

Molecular design is a central task in drug discovery that requires precise structural reasoning and domain knowledge. While large language models (LLMs) have shown promise in generating high-level editing intentions in natural language, they often struggle to faithfully execute these modifications, particularly when operating on non-intuitive representations like SMILES. We introduce MECo, a framework that bridges reasoning and execution by translating editing actions into executable code. MECo reformulates molecular modification for LLMs as a cascaded framework: generating human-interpretable editing intentions from a molecule and design objective, followed by translating those intentions into executable structural edits via code generation. Our approach achieves over 98% accuracy in reproducing held-out realistic edits derived from chemical reactions and target-specific compound pairs. On downstream benchmarks spanning physicochemical properties and target activities, MECo substantially improves consistency by 38-86 percentage points to 90%+ and achieves higher success rates over SMILES-based baselines while preserving structural similarity. By aligning intention with execution, MECo enables consistent, controllable and interpretable molecular design, laying the foundation for high-fidelity feedback loops and collaborative human-AI workflows in drug discovery.

cs.LG↗
arXiv2026

RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control

Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while controlled action--response trajectories remain comparatively scarce and costly to collect. This observation--intervention asymmetry is a central obstacle to building practical world models for RAN control. We address this problem with RAN-JEPA, an action-conditioned world model that separates representation learning from intervention learning. The model first learns a predictive latent representation from observation-only network data, adapts that representation to the target deployment domain, and then learns action-conditioned latent dynamics from controlled sleep/wake trajectories while keeping the encoder fixed. We evaluate RAN-JEPA using public operator performance data for pretraining and a real-equipment four-cell 5G testbed for domain adaptation, post-training, and control. Across four future 15-minute intervals, RAN-JEPA achieves lower action-conditioned prediction error than a GPT-2 world-model baseline and a mechanistic rule, while remaining close to a strong persistence reference. What-if evaluation further shows that the model produces distinct and coherent future trajectories under matched SLEEP and KEEP plans. In closed-loop control, RAN-JEPA consistently supports higher sleep ratios than the two baselines at comparable congestion cost. These results show that observation-first, action-conditioned learning can turn abundant passive telemetry and limited intervention data into a practical predictive model for energy-aware RAN control.

cs.AI↗
arXiv2026

Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence

Reinforcement learning has become the foundational paradigm for enhancing the reasoning capabilities of LLMs. Yet the dominant approach, Proximal Policy Optimization (PPO), relies on a geometrically degenerate clipping proxy that cannot adapt its resistance to policy shifts, leading to premature clipping and degraded exploration. Subsequent variants alleviate these issues through fragmented and heuristic modifications. We propose Generalized Proximal Policy Optimization (GPPO), a principled and unified framework for understanding and designing LLM RL algorithms through the lens of divergence. We establish a generalized $f$-divergence trust-region theory with a monotonic performance improvement guarantee, and show that different $f$-divergences induce distinct geometries and policy update dynamics. We further introduce novel estimator topologies that provide more faithful divergence estimates than the conventional single-sample Monte Carlo estimation. Under this framework, PPO and recent variants such as DAPO, DPPO, and RIPO emerge as special cases, establishing a principled two-dimensional design space of {Divergence $\times$ Estimator}. Extensive experiments on eight competition-level math and coding benchmarks show that both dimensions are critical. The best-performing GPPO instantiation surpasses standard GRPO by up to 50% and 14% on math and coding, delivering SOTA performance.

cs.LG↗
arXiv2026

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fundamental flaw of PPO-Clip: it implicitly measures policy discrepancy using Euclidean metric, which is theoretically inconsistent with the intrinsic geometry on the policy Riemannian manifold. This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration. To correct this geometric flaw, we propose Riemannian Isometric Policy Optimization (RIPO), which guarantees isometric policy updates on the Riemannian manifold, effectively balancing exploration and exploitation. We further show that RIPO achieves a favorable bias-variance trade-off, which stabilizes optimization. Extensive experiments demonstrate that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks (up to 60% improvement over GRPO on AIME24).

cs.LG↗
arXiv2026

Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy

As the bridge between protein modality and discrete modeling, protein structure tokenization still largely relies on heavily engineered training objectives tailored to specific downstream tasks and large training datasets, which hinders its transfer to broader application scenarios. To address this issue, we propose ProFiT, a lightweight flow matching tokenizer. With simple training strategies that encourage healthy codebook utilization, ProFiT can be trained efficiently and naturally learns semantically meaningful representations without any manual semantic alignment, while achieving reconstruction quality and generalization that match or surpass those of substantially larger tokenizers. We conduct extensive evaluations across a wide range of settings and demonstrate that ProFiT is a plug-and-play tokenizer adaptable to diverse downstream tasks. This study further reveals the significant potential of the flow matching tokenizer paradigm. Our code is publicly available at https://github.com/QDKStorm/ProFiT.

cs.LG↗
arXiv2026

PFArena: Benchmarking Language Models for Protein Modification

Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs), large language models (LLMs), and LLM-based agents have shown promise in protein modification, their relative efficacy across realistic experimental decision-making settings remains unclear. To bridge this gap, we introduce PFArena, a benchmark comprising four controlled task interfaces that cover single-mutant generation and multi-mutant ranking. By providing varying levels of mutation fitness data, PFArena reflects four representative research scenarios characterized by differing degrees of prior experimental context. We assess six PLMs, six LLMs, and five LLM-based agents using complementary metrics to measure both peak and overall protein modification performance. Our evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly when target-specific fitness data are available. Nevertheless, all model families face fundamental challenges with increasing search-space size and mutation depth. We release our code and benchmark suite to facilitate reproducible research in model-assisted protein modification.

cs.AI↗
arXiv2026

GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation

Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and visual-prediction objectives may omit critical physical and task structure while retaining control-irrelevant visual redundancy. We call this mismatch between visual richness and control utility the action-sufficiency gap. We investigate whether this gap can be bridged by guiding intermediate features to preserve three control-relevant structure in robotic manipulation: geometry governing motion feasibility, affordance encoding instruction-relevant entities, and goals grounding instructions in task-relevant regions. To this end, we present GIFT (Guided Intermediate Feature Training), an architecture-flexible framework for learning intermediate features that translates these structures into training-time constraints through geometry alignment, affordance prediction, and goal-region reconstruction. We instantiate GIFT in a Vision-Language-Action (VLA) policy, a direct-action World-Action Model (WAM), and an inverse-dynamics WAM while retaining each model's action formulation. Under zero-shot transfer to LIBERO-Plus, GIFT-VLA, GIFT-WAM-Fast, and GIFT-WAM-IDM outperform StarVLA-OFT, Fast-WAM, and Fast-WAM-IDM by 4.6, 12.6, and 5.2 points, reaching 79.6%, 72.6%, and 87.8%, respectively. On RoboCasa, the three GIFT variants reach 61.4%, 83.6%, and 82.3%, outperforming their counterparts by 12.6, 9.0, and 8.4 points, respectively. Together, these results establish learning functionally structured intermediate features as a reusable principle across model-specific action formulations, with especially large gains on articulated-object tasks and high-precision real-world manipulation under unseen visual and spatial perturbations. Project page: https://openphoenix-team.github.io/GIFT-pages.

cs.RO↗
arXiv2026

Latent Action as Intention Enables Efficient Future Imagination for World Action Models

World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substantial latency. Fast-WAM removes this process for efficiency; however, our matched implementations show lower generalization for Fast-WAM than for future-aware alternatives, especially with scarce robot demonstrations and in out-of-distribution scenarios. To bridge this gap, we introduce **LAWA**, a WAM architecture that uses compact latent actions as an operational representation of future intentions, enabling efficient test-time future imagination without generating future observations. Specifically, a discrete tokenizer enhanced by action-free pre-training produces manipulation-centric codebook targets. LAWA jointly denoises a continuous latent state anchored to these targets with executable action chunks while omitting the future-video branch at inference. On RoboCasa, LAWA achieves state-of-the-art average success rates of 65.6% and 80.8% in the few-shot and full data settings, improving over the matched Fast-WAM baseline by 9.6 and 4.5 points, respectively. It also preserves the performance level of the matched Joint-WAM variant while requiring 42.9% lower inference latency. LAWA also demonstrates competitive zero-shot robustness on LIBERO-Plus and superior performance on real-world tasks. These results show that future imagination need not be discarded: retaining it with compact latent actions yields an effective trade-off among performance, generalization, and latency. Code and models will be released.

cs.RO↗
arXiv2026

Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

cs.LG↗
arXiv2026

State2State: Environment-Derived Mid-Training for LLM Agents

Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Though effective, both remain bottlenecked by externally specified tasks and supervision signals, limiting the scalability and diversity of agent training. We study an environment learning paradigm in which agents acquire interaction and manipulation capabilities solely through environment interaction, without externally specified tasks. We propose State2State, an environment-derived mid-training method that converts explored environment states into training objectives, challenging agents to reach a specified target state. By deriving tasks from environment exploration and verifying success through rule-based state matching, State2State provides scalable and verifiable training objectives without expert supervision or manual task design. Experiments on ALFWorld and ScienceWorld show that State2State improves agent performance as a standalone environment-learning stage in most settings. As initialization for downstream RL, it further improves final performance and learning efficiency, with promising evidence of cross-environment generalization.

cs.CL↗
arXiv2026

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate challenge in long-text processing. We directly optimize for long-text tasks in an end-to-end fashion and introduce a novel agent workflow, MemAgent, which reads text in segments and updates the memory using an overwrite strategy. We extend the DAPO algorithm to facilitate training via independent-context multi-conversation generation. MemAgent has demonstrated superb long-context capabilities, being able to extrapolate from an 8K context trained on 32K text to a 3.5M QA task with performance loss < 5% and achieves 95%+ in 512K RULER test.

cs.CL↗
arXiv2026

Never compromise with vulnerabilities: a comprehensive survey on AI governance

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including misinformation, inequity, security breaches, physical harm, and eroded public trust. These challenges highlight the urgent need for robust AI governance. We propose a comprehensive framework integrating technical and societal dimensions, structured around three interconnected pillars: Intrinsic Security (system reliability), Derivative Security (real-world harm mitigation), and Social Ethics (value alignment and accountability). Uniquely, our approach unifies technical methods, emerging evaluation benchmarks, and policy insights to promote transparency, accountability, and trust in AI systems. Through a systematic review of over 300 studies, we identify three core challenges: (1) the generalization gap, where defenses fail against evolving threats; (2) inadequate evaluation protocols that overlook real-world risks; and (3) fragmented regulations leading to inconsistent oversight. These shortcomings stem from treating governance as an afterthought, rather than a foundational design principle, resulting in reactive, siloed efforts that fail to address the interdependence of technical integrity and societal trust. To overcome this, we present an integrated research agenda that bridges technical rigor with social responsibility. Our framework offers actionable guidance for researchers, engineers, and policymakers to develop AI systems that are not only robust and secure but also ethically aligned and publicly trustworthy. The accompanying repository is available at https://github.com/Tele-EVOL/AI-Governance.

cs.CR↗
arXiv2026

On the Identifiability of Controlled World Models

World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framework for learning such models in representation space. Its action-conditioned extension plays a central role in visual control and latent-space planning, but leaves a fundamental question: can it recover the controlled dynamics from nonlinear observations? This paper presents a joint identifiability condition for controlled world models with Gaussian latent states, which consists of two coupled components: (1) representation identifiability and (2) transition identifiability. The former depends on the spectral separation property while the latter is related to non-degenerate variation of conditional action. We prove that when this condition holds, minimizing the LeJEPA-style predictive objective can recover both latent states and controlled dynamics in the sense of orthogonal transformation. We further prove that the upper bound of transition prediction error is inversely proportional to the spectral separation margin. We also characterize an attainable amplification of counterfactual prediction error that scales inversely with the weakest conditional action-excitation margin. The theoretical predictions are empirically supported across four nonlinear observation settings.

cs.LG↗
arXiv2026

E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios

Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench decouples environment synthesis from task synthesis: graph-guided database filling builds reusable, orphan-free product environments, while generator-solver asymmetry creates tasks with both an information gap and a tool gap, requiring agents to discover hidden data and compose multiple tool calls before changing state. Outcomes are graded deterministically by database-state diffs. Since both environments and tasks are synthetic, E-Bench is controllable at the environment level and scalable at the task level. Benchmarking 11 cutting-edge LLMs shows that multi-step tool use remains challenging: Pass^3 stays below 60% for the strongest models, and even with code execution in the E-Bench-Code extension, reliability (Pass^3) remains below 70%.

cs.AI↗
arXiv2026

Weak-to-Strong Generalization via Direct On-Policy Distillation

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck. We study a weak-to-strong alternative: run RL on a smaller model where rollouts are cheaper, then reuse what that RL run learned to improve a stronger target model. Directly distilling the post-RL weak teacher is not enough, because the teacher's final policy mixes useful RL gains with the limitations of the smaller model. We propose Direct On-Policy Distillation (Direct-OPD), which transfers the teacher's RL-induced policy shift instead. Direct-OPD compares the post-RL teacher with its own pre-RL reference and treats their log-ratio as a dense implicit reward for the student. In plain terms, the checkpoint pair tells us which actions RL made the weak model more or less likely to take, and Direct-OPD applies that signal on the stronger student's own on-policy states. This directly reuses the weak model's RL supervision signal without running sparse-reward RL on the target model. Empirically, Direct-OPD consistently leverages weaker teachers to improve stronger target models; notably, it boosts Qwen3-1.7B from 48.3% to 58.3% on AIME 2024 in just 4 hours on 8 A100 GPUs. It outperforms step-matched direct RL and enables the sequential composition of multiple policy shifts. Our results show that RL outcomes can be reused across model scales as implicit reward signals, not merely as final models to imitate.

cs.LG↗
arXiv2026

Spectral Rewiring for Exploration, Purification, and Model Merging

Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed reasoning performance, often reflected by premature saturation of test-time scaling, and interference when consolidating multiple capabilities through multi-domain training or model merging. We show that the reasoning-effective component of these updates is largely concentrated in the base model's spectral space, motivating Subspace-Aligned Rewiring (SAR), a post-hoc editing method that retains this spectral core while removing orthogonal components. SAR therefore preserves reasoning gains and filters residual update directions that suppress performance or amplify cross-domain interference. Across several model families and scales, SAR extracts compact reasoning cores using as little as approximately 0.58% of total parameters: it preserves over 99% of post-training performance and improves high-k exploration in mathematical reasoning, and generalizes to agentic coding by improving six of seven open benchmarks on an in-house model. SAR also purifies mixed-domain training updates by releasing suppressed coding capability while maintaining math reasoning and instruction following. It further enables model merging across experts, yielding cross-domain generalization that surpasses previous merging baselines and even the best single-domain experts. Overall, SAR shows that extracting reasoning-effective updates from parameter geometry can serve as a training-free mechanism to improve reasoning and multi-domain performance.

cs.LG↗
arXiv2026

Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks

Large language models (LMs) offer broad generalization capabilities but require vast amounts of data and computational resources for domain-specific tasks; small models (SMs), in contrast, are more efficient and tailored to specific domains yet lack general-purpose coverage. Taking a collaborative approach, where large and small models work synergistically, can accelerate the adaptation of LLMs to private domains and unlock new potential in AI. This survey presents a comprehensive overview of recent advances and challenges in harnessing the collaborative power of large and small models for private-domain adaptation. It specifically focuses on the unique constraints of cross-boundary environments, where models belong to distinct parties, and examines the resulting tensions among data privacy, model security, integrity, and resource limitations. By analyzing the information flow between distinct model and data stakeholders, we propose a unified taxonomy that classifies research into three primary directions: downward knowledge transfer (LM to SM), upward knowledge transfer (SM to LM), and inference-time collaboration across parties. Drawing on this taxonomy, we analyze the core challenges inherent to cross-boundary information exchange, including data-privacy, model-security, and integrity threats as well as efficiency constraints, and synthesize these into a multi-objective optimization problem that governs practical deployment. Finally, we review key open challenges inherent to such hybrid approaches and outline promising directions for future research. By offering a principled, boundary-centric view of this rapidly evolving landscape, this survey aims to serve as a structured resource for researchers and practitioners advancing privacy-aware, resource-efficient AI deployment.

cs.LG↗