arXiv subjects

Tao Zhong

Publications and source records attributed to Tao Zhong.

At least 19 recordsLinked to original sources

arXiv2026

Collab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programming

Mixed-integer linear programming (MILP) has been a fundamental problem in combinatorial optimization. Conventional MILP solving mainly relies on carefully designed heuristics embedded in the branch-and-bound framework. Driven by the strong capabilities of neural networks, recent research is exploring the value of machine learning alongside conventional MILP solving. Although learning-based MILP methods have shown great promise, existing works typically learn policies for individual modules in MILP solvers in isolation, without considering their interdependence, which limits both solving efficiency and solution quality. To address this limitation, we propose Collab-Solver, a novel multi-agent-based policy learning framework for MILP that enables collaborative policy optimization for multiple modules. Specifically, we formulate the collaboration between cut selection and branching in MILP solving as a Stackelberg game. Under this formulation, we develop a two-phase learning paradigm to stabilize collaborative policy learning: the first phase performs data-communicated policy pretraining, and the second phase further orchestrates the policy learning for various modules. Extensive experiments on both synthetic and large-scale real-world MILP datasets demonstrate that the jointly learned policies significantly improve solving performance. Moreover, the policies learned by Collab-Solver have also demonstrated excellent generalization abilities across different instance sets.

cs.AI↗

arXiv2026

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. However, the optimization behavior of ES remains understudied, making it hard to define its advantage scope compared to mainstream post-training paradigms (e.g., Group Relative Policy Optimization (GRPO)). By systematically investigating ES dynamics and mechanisms, this paper first identifies a performance advantage of ES over GRPO, theoretically and empirically showing that ES can lead to broader reasoning coverage, thereby better exploiting the reasoning capabilities of pretrained LLMs. Theoretically, we show that verifier-projected Jensen-Shannon diversity across the ES population is helpful to higher Pass@K performances. Empirically, unlike GRPO, which exhibits entropy collapse, ES improves Pass@1 while attaining higher Pass@K than GRPO. We further develop a sequential GRPO-ES training strategy that combines GRPO's strength in Pass@1 with ES's gains in Pass@K. Second, we find that despite substantial whole-model parameter drift, the task-performance gains of ES are only contributed to a sparse subset of larger-magnitude updates. This functional sparsity suggests that large parameter movement need not imply widespread functional change, and held-out evaluations further show that it does not necessarily lead to catastrophic forgetting. Finally, we study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM. These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO.

cs.LG↗

arXiv2026

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptimal settings can degrade solving time by orders of magnitude. Default configurations are often suboptimal, while traditional tuning methods either suffer from the ``cold-start'' problem and inefficient search or heavily rely on expert experience. This paper introduces \textbf{GRIMIP} (\textbf{\underline{G}}eneral \textbf{\underline{R}}easoning for \textbf{\underline{I}}nstance-specific \textbf{\underline{MIP}} configuration), a novel hybrid intelligence framework that synergistically integrates the semantic reasoning capabilities of Large Language Models (LLMs) with the sample-efficient search of Bayesian Optimization (BO). GRIMIP enables the LLM to function as a complete probabilistic surrogate within the BO loop, significantly improving performance and reducing sampling and evaluation costs. On seven benchmarks including MIPLIB, GRIMIP achieves over 40\% reduction in Primal-Dual Integral on hard instances, outperforming SMAC and other LLM-assisted BO methods. By granting LLMs sufficient autonomy, GRIMIP combines the expert-level reasoning of LLMs with the efficient search of BO, achieving state-of-the-art performance.

cs.LG↗

arXiv2026

Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control

Multi-agent reinforcement learning (MARL) policies for swarm control often learn inefficiently and generalize poorly across coordinate frames, team sizes, and agent roles. We introduce Local-Canonicalization Equivariant Graph Neural Networks (LEGO), a modular policy architecture that combines agent-centric canonicalization with role-aware graph encoding. Canonicalization removes dependence on the global coordinate frame, while transforming predicted local actions back to the world frame produces an E(2)-equivariant policy. Role-wise graph encoders provide intra-role permutation equivariance and fixed-dimensional representations for variable-size teams. LEGO can be paired with standard MARL algorithms; we instantiate it with MAPPO. Across cooperative MPE Spread and competitive Tag-occlusion benchmarks, LEGO-MAPPO improves sample efficiency and task performance relative to MLP-based, graph-only, canonicalization-only, and equivariant baselines. The learned policies transfer without fine-tuning to unseen team sizes, maintain performance under spatial distribution shifts, and benefit from curriculum initialization for larger teams. In Crazyflie experiments, the policy remains operational after one pursuer is disabled. Code is available at https://github.com/CAB-Lab-Princeton/LEGO-MARL.

cs.RO↗

arXiv2026

Singly Cabibbo-suppressed hadronic weak decays of the $Ω^-$ hyperon

We study the two-body hadronic weak decays of the $Ω^-$ hyperon with strangeness $S=-3$, including three singly Cabibbo-suppressed decay modes: $Ξ^0 π^-$, $Ξ^-π^0$ and $ΛK^-$. The decay amplitudes at the quark level, arising from $s\to ud \bar{u}$ transitions (direct pion emission and color-suppressed processes) and $su\to ud$ transitions (pole terms), are calculated in the framework of the non-relativistic constituent quark model.The theoretical results show that the $Ξ^0 π^-$ channel is dominated by the color-allowed direct pion emission process, while the $ΛK^-$ channel is well described by one type of pole contribution mediated through intermediate $Ξ$ resonances ($1^2S_{1/2^+}$ and $1^2P_{1/2^-}$ states). However, the contribution from tree-level mechanisms alone to the branching ratio of $Ω^- \to Ξ^- π^0$ is small due to its color-suppressed nature. The discrepancy is resolved by including final state interactions through rescattering processes via intermediate states $Ξ^0π^-$ and $ΛK^-$. This work demonstrates that a unified description of $Ω^-$ hadronic weak decays necessitates the interplay of quark-level weak vertices, baryon pole structures, and long-distance final state rescattering dynamics. With these mechanisms, the obtained branching ratios are in agreement with the high-precision experimental data from the BESIII. Furthermore, these above decays are found to be dominated by the parity-conserving $P$-wave transitions, thus the asymmetry parameters are almost zero.

hep-ph↗

arXiv2026

Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory

Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can be used at once. Existing systems mainly follow two strategies: memory retention and memory consolidation. Retention keeps raw records and preserves exact details, but relevant evidence may not fit under a tight budget; consolidation compresses and combines records, improving coverage per token but risking the loss of query-critical details. Neither strategy is universally preferable. This raises two central questions: when should consolidation replace retention, and which operator -- Merge, Abstract, or Rewrite -- should be selected? We formalize this decision by decomposing each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits. Their balance explains why the preferred action changes with relative budget pressure. We implement this mechanism with Offline Abstraction-Safety (OAS), a lightweight learner that estimates action utilities from pre-generation features with held-out harm calibration. The public LongMemEval and LoCoMo benchmarks show the same budget-dependent pattern. On LongMemEval, consolidation improves absolute accuracy by up to 48% under tight budgets, whereas retention is preferable under loose budgets; LoCoMo replicates this crossover at a smaller budget, consistent with its shorter evidence. On both datasets, cross-note abstraction and merging generally outperform local rewriting when compression is necessary.

cs.AI↗

arXiv2026

Vector mesons leading-twist longitudinal distribution amplitudes and related semi-leptonic decays within QCD sum rules

In this work, we focus on the light vector meson leading-twist longitudinal distribution amplitudes (DAs) $ϕ^\parallel_{2;V}(x,μ)$ with $V = ρ, K^\ast, ϕ$. In order to obtain their accurate behaviors, a new scheme of QCD sum rule research with respect to DA suggested in 2021 by us is adopted. With an improved sum rule formula, the $ξ$-moments $\langleξ^n\rangle_{2;V}^\parallel$ up to tenth order are calculated. In which, $\langleξ^2\rangle^\parallel_{2;ρ}=0.225^{+0.013}_{-0.012}$, $\langleξ^1\rangle^\parallel_{2;K^\ast}=-0.0228^{+0.0042}_{-0.0040}$, $\langleξ^2\rangle^\parallel_{2;K^\ast}=0.217^{+0.007}_{-0.007}$, $\langleξ^2\rangle^\parallel_{2;ϕ}=0.209^{+0.020}_{-0.020}$, and the corresponding Gegenbauer moments $a^{2;\parallel}_{2;ρ}=0.074^{+0.039}_{-0.036}$, $a^{1;\parallel}_{2;K^\ast}=-0.038^{+0.007}_{-0.007}$, $a^{2;\parallel}_{2;K^\ast}=0.050^{+0.020}_{-0.019}$, $a^{2;\parallel}_{2;ϕ}=0.027^{+0.058}_{-0.058}$ at the scale $μ= 1~{\rm GeV}$, respectively. By fitting those $\langleξ^n\rangle^\parallel_{2;V}(n = 1,2,\cdots,10)$ with the least squares method, the behaviors of leading-twist longitudinal DAs for $ρ, K^\ast, ϕ$ are determined. Further, we recalculate the transition form factors and branching ratio of the $D\to(ρ,K^\ast)$, $D_s\toϕ$ semi-leptonic decay processes.

hep-ph↗

arXiv2026

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budget feasibility, evidence utility, and delayed costs including miss, reacquisition, and stale penalties. We show this multi-step problem is NP-hard, making exact solution intractable. Moreover, deployment decisions must be made under partial observability. To address these challenges, we propose OSL-MR (Observability-Safe Learning for Memory Retention), a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision. OSL-MR combines an evidence learner trained from realized evidence with a Mixed-Score heuristic that serves as a deployable online-safe baseline and an inductive prior. The policy learns query-conditioned evidence from interaction data and remains deployable under the same constraints. Experiments on LoCoMo and LongMemEval show OSL-MR outperforms recency-based, Generative Agents-style, and other heuristic baselines, especially under tight budgets. The Mixed-Score prior improves precision and recall, and sensitivity analysis shows robustness across cost settings. On small solvable instances, single-step optimization is insufficient to anticipate future demand shifts, while OSL-MR stays significantly closer to the dynamic-programming optimum, confirming the necessity of the sequential formulation and reinforcing our learning-guided approximation. These results establish constrained stochastic optimization and optimization-guided learning as a principled foundation for memory management in long-horizon agents.

cs.AI↗

arXiv2026

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data generation pipelines remain static and decoupled from model learning. To address these challenges, we propose EvoOptiGraph, a novel framework where data and model co-evolve, driven by model weaknesses. EvoOptiGraph represents each mixed-integer linear program (MILP) as an attributed bipartite graph and applies validity-preserving evolutionary operators to generate structurally diverse instances. The evolved graphs are converted into solver code and natural language via deterministic compilation and verified back-translation. Training proceeds in two stages: supervised fine-tuning (SFT) on an initial dataset, followed by reinforcement learning with verifiable rewards (RLVR), where graph-derived weakness signals guide the generation of new instances targeting the model's failures. This forms a closed loop that continuously updates the training distribution. Empirical results on six public datasets show that EvoOptiGraph significantly outperforms larger generalist models, agentic methods, and specialized baselines in accuracy, executability, and generalization. These results demonstrate that targeted data-model coevolution is an effective strategy for improving LLMs on optimization modeling tasks.

cs.AI↗

arXiv2026

ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information

Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce distribution drift. Standard behavior-corrected methods control this drift with behavior-policy probabilities, importance ratios, or clipping, which requires token-aligned, versioned, and numerically consistent behavior log-probabilities across rollout and learner systems. We ask whether asynchronous group-relative RL can instead be stabilized using only current-policy probabilities. We identify a scale-imbalance failure mode: when stale responses are evaluated under the current policy, positive and negative loss terms can appear at different negative log-probability scales, so zero-sum advantages no longer imply balanced loss contributions. We propose Asymmetric-Scale Policy Optimization (ASymPO), which normalizes each response's token loss by its current average token negative log-probability. ASymPO requires no behavior-policy probabilities, restores response-level zero-sum balance, and preserves a nonzero learning signal. We also introduce Scaled Policy Optimization (SPO), a fixed negative-scaling baseline, and evaluate both current-policy-only objectives in asynchronous mathematical reasoning post-training.

cs.LG↗

arXiv2026

Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction

Endpoint detection (EPD) is essential for natural turn-taking in streaming speech systems. However, reliably determining the endpoint of an utterance is challenging because speakers often pause mid-utterance due to hesitations and disfluencies. Semantic EPD has emerged as a promising direction to address this issue but is hindered by ambiguous supervision and strict streaming constraints. We propose Next-Turn that uses the time-to-next-speech-onset as the training objective, where targets are derived directly from speech timestamps and require no additional annotation. Experiments show that the proposed method outperforms conventional acoustic and recent semantic EPD baselines, achieving a 25.9% absolute improvement in endpoint accuracy within 320 ms over the strongest baseline. In addition, joint training with the duration-aware objective complements standard binary EPD, with gains that increase monotonically with increasing pauses.

cs.SD↗

arXiv2026

Towards Personalized Federated Learning for Dysarthric Speech Recognition

Speech recognition is challenging for dysarthric speakers. While federated learning (FL)-based ASR can be an effective tool for protecting privacy, it suffers from heterogeneity issues caused by speaker variability. Forcing all speakers to share the same model components can be suboptimal under such heterogeneity, making personalization a promising direction; however, related research on dysarthric speech remains limited. To this end, this paper explores two aggregation strategies to achieve personalization, including the parameter-based averaging strategy and the embedding-based averaging strategy. Experiments on UASpeech and TORGO show that the proposed methods outperform the baseline regularized FedAvg by statistically significant WER reductions of up to 0.99% absolute (3.15% relative) on UASpeech and 0.56% absolute (4.73% relative) on TORGO, respectively.

cs.SD↗

arXiv2026

IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems

Full-duplex spoken dialogue models allow voice agents to listen and speak concurrently, enabling natural interaction with real-time overlap. However, end-to-end dual-channel models that jointly encode user and agent streams may degrade in realistic acoustic environments: interfering speakers leaking into the user microphone can be encoded as part of the user query, corrupting the LLM's conditioning and causing unstable turn-taking and reduced response quality. We propose Interference-Resilient Adaptive Fusion (IRAF), a lightweight, streaming-compatible module that modulates the contribution of user audio to the LLM frame by frame. IRAF predicts a scalar reliability gate from target-speaker and user audio embeddings and rescales user representations before fusion with agent embeddings. Experiments on MS-MARCO and InstructS2S-200K show consistent gains in response quality and full-duplex interaction under interfering-speaker conditions.

cs.SD↗

arXiv2026

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens.

cs.AI↗

arXiv2026

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling

Large language models (LLMs) have opened new paradigms in optimization modeling by enabling the generation of executable solver code from natural language descriptions. Despite this promise, existing approaches typically remain solver-driven: they rely on single-pass forward generation and apply limited post-hoc fixes based on solver error messages, leaving undetected semantic errors that silently produce syntactically correct but logically flawed models. To address this challenge, we propose SAC-Opt, a backward-guided correction framework that grounds optimization modeling in problem semantics rather than solver feedback. At each step, SAC-Opt aligns the original semantic anchors with those reconstructed from the generated code and selectively corrects only the mismatched components, driving convergence toward a semantically faithful model. This anchor-driven correction enables fine-grained refinement of constraint and objective logic, enhancing both fidelity and robustness without requiring additional training or supervision. Empirical results on seven public datasets demonstrate that SAC-Opt improves average modeling accuracy by 7.7%, with gains of up to 21.9% on the ComplexLP dataset. These findings highlight the importance of semantic-anchored correction in LLM-based optimization workflows to ensure faithful translation from problem intent to solver-executable code.

cs.AI↗

arXiv2026

Topology-Preserving Neural Operator Learning via Hodge Decomposition

In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resolves spectral interference by isolating unlearnable topological degrees of freedom from learnable geometric dynamics, enabling an additive approximation confined to structure-preserving subspaces. Building on Hodge theory and operator splitting, we derive a principled operator-level decomposition. The result is a Hybrid Eulerian-Lagrangian architecture with an algebraic-level inductive bias we call Hodge Spectral Duality (HSD). In our framework, we use discrete differential forms to capture topology-dominated components and an orthogonal auxiliary ambient space to represent complex local dynamics. Our method achieves superior accuracy and efficiency on geometric graphs with enhanced fidelity to physical invariants. Our code is available at https://github.com/ContinuumCoder/Hodge-Spectral-Duality

cs.LG↗

arXiv2026

Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification

Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language models (LLMs) to automate this modeling process. However, existing works often struggle to verify the correctness of the generated optimization models, without checking the rationality of the constraints and variables or the validity of solutions to the generated models. This hampers the subsequent verification and correction steps, and thus it severely hurts the modeling accuracy. To address this challenge, we propose a novel LLM-based framework with Dual-side Verification (Opt-Verifier) from both structure and solution perspectives, thereby improving the modeling accuracy. The structure-side verification ensures that the modeling structure of the generated optimization models aligns with the original problem description, accurately capturing the problem's constraints and requirements. Meanwhile, the solution-side verification interprets and evaluates the solutions' validity, confirming that the optimization models are logically and mathematically sound. Experiments on popular benchmarks demonstrate that our approach achieves over 20\% improvement in accuracy.

cs.AI↗

arXiv2026

Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation

Inverse problems for stiff parabolic partial differential equations (PDEs), such as the inverse heat conduction problem (IHCP), are severely ill-posed: the forward map rapidly damps high-frequency interior structure before it reaches the boundary. Soft-constrained physics-informed neural networks (PINNs), which embed the PDE as a residual penalty, suffer from gradient pathology in this regime and tend to fit boundary measurements while leaving the interior field essentially untouched. We propose Neural Field Thermal Tomography (NeFTY), a hard-constrained neural field framework for label-free three-dimensional inverse heat conduction. NeFTY represents the unknown diffusivity as a continuous coordinate-based neural network, and at every optimization step passes the candidate field through a differentiable implicit-Euler heat solver with harmonic-mean interface flux, so that the governing PDE holds exactly on the discretization rather than as a soft penalty. Adjoint gradients propagate the surface reconstruction error back to the network weights at solver-level memory cost, making test-time inversion tractable on a single GPU. Across synthetic 3D benchmarks, NeFTY substantially outperforms soft-constrained PINN variants and a voxel-grid baseline on label-free volumetric recovery, and it transfers to real thermography data, surpassing classical signal-processing baselines in both defect segmentation and depth estimation. Additional details at https://cab-lab-princeton.github.io/nefty/

cs.LG↗