Search arXiv⌕ Search

arXiv subjects

Bo Li

Publications and source records attributed to Bo Li.

At least 37 records · Page 2Linked to original sources
arXiv2026

Maximizing Reaction via Spatial Localization: A PDE-Constrained Variational Approach

We study a PDE-constrained variational problem for the optimal spatial distribution of a catalytic material reacting with a substrate in a biological or materials system. With a given catalyst concentration, the substrate concentration is determined by a reaction-diffusion equation. The reaction functional for the catalyst concentrations is defined to be the total reaction output, which is the product of catalyst and substrate concentrations. Both the linear and Michaelis-Menten reaction kinetics are considered. We construct reaction-maximizing sequences through the localization of catalysts using barrier functions and show the non-existence of a global maximizer. We also derive the first and second variations of the reaction functional. By constructing a competing catalyst concentration, we show the non-existence of a local maximizer. Based on our analysis, we propose a regularized variational model and prove the existence of its global maximizer.

math.AP↗
arXiv2026

AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents

LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as agents read and write sensitive user data across email, documents, and other applications, a central privacy question is whether they preserve contextual integrity (CI), that is, whether the information flows they produce comply with context-specific disclosure constraints. Existing work either focuses on model-level privacy leakage or evaluates agents in limited application environments with manually constructed disclosure constraints. In this work, we introduce AgentCIScope, a unified platform and benchmark for evaluating agent-level contextual integrity through executable, multi-step tasks across diverse, realistic application environments. AgentCIScope transforms public and synthetic privacy cases into executable agent tasks, with disclosure constraints grounded in three criteria: governing privacy policies, persona-based agreement, and a predefined sensitive-attribute taxonomy. Based on AgentCIScope, we evaluate 12 agents on 936 tasks and find that strong task-completion capability does not guarantee contextual-integrity preservation: single-run leakage rates range from 32.5% to 94.4%, while repeating each task five times further increases leakage by 4-19 percentage points. Leakage varies substantially across attributes: personal preferences and booking details have average leakage rates of 84.7% and 76.5%, compared with 17.1% for credit-card information and 29.4% for SSNs; environments: calendar has the highest average leakage rate as an information source, while WhatsApp ranks highest as an information destination; and governing privacy policies. AgentCIScope provides deep insights into agent privacy leakage and serves as a unified testbed for developing privacy-preserving agents.

cs.AI↗
arXiv2026

RewardHarness: Self-Evolving Agentic Post-Training

Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference data. This limitation is particularly evident in evaluating instruction-guided image edits, even though humans can often learn such preferences from only a few examples. We present RewardHarness, a training-free, self-evolving agentic reward framework that reframes reward modeling as context evolution rather than weight optimization. Instead of learning from large-scale annotations, RewardHarness aligns with human preferences by iteratively evolving a library of tools and skills from as few as 100 preference demonstrations. Given a source image, an edited image, and an editing instruction, an orchestrator agent selects the most relevant subset of tools and skills from the maintained library, and sub-agents invoke them to construct a reasoning chain that produces a reward score. By comparing predicted scores with ground-truth preferences and analyzing successes and failures in the reasoning process, the orchestrator automatically refines its library of tools and skills without additional human annotation. Using only 0.05% of the EditReward preference data, RewardHarness achieves 47.4% average accuracy on EditReward-Bench K=2/3/4 and GenAI-Bench, surpassing GPT-5 by 5.3 points. When used as a reward signal in FlowGRPO, RL-tuned models achieve 3.52 on ImgEdit-Bench. Code and model are available at the project page: https://rewardharness.com/

cs.AI↗
arXiv2026

Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation

Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization. However, applications such as AR/VR and interactive gaming further require stereo audio to provide an immersive sense, which remains largely overlooked. Effective stereo audio requires the perceived sound location to evolve consistently with the motion of its corresponding visual source. We refer to this property as Dynamic Spatial Correspondence and propose StereoBind, a framework that binds visual source motion to stereo sound generation. StereoBind uses motion tracks to coordinate visual motion and stereo audio through three complementary mechanisms. Visual Motion Binding establishes source-aware audiovisual correspondence, the Spatial Track Encoder captures absolute source positions, and Residual Track RoPE models relative motion. For supervision and evaluation, we construct StereoWorld-29K, a large-scale stereo audio-video dataset with paired motion tracks, and StereoWorldBench for measuring audiovisual spatial consistency. Experiments show that StereoBind substantially improves spatial alignment in stereo audio generation over existing models while preserving overall audiovisual quality.

cs.CV↗
arXiv2026

Accelerating MoE Training through Expert Placement and Replica Coordination

Distributed training of sparsely activated mixture-of-experts (MoE) models is often bottlenecked by workload imbalance and all-to-all (A2A) communication induced by dynamic token routing. Existing token deduplication, expert placement, and replication techniques alleviate these bottlenecks but do not jointly capture their distinct load semantics. Under hierarchical token deduplication, communication counts each token once per destination group at each hierarchy level, whereas expert computation processes every token-expert assignment. With replication, both costs depend jointly on physical layout and token-to-copy mapping, making separate optimization suboptimal. We present PlaceMoE to address this coupling. First, we formulate the joint optimization of expert layout and source-aware token-to-copy mapping for E experts distributed across P devices, accounting for both hierarchical communication traffic and expert-compute load. Second, we develop a solver that combines co-selection-aware expert grouping, bounded dynamic programming for replica allocation, and alternating refinement of layout and mapping. Third, PlaceMoE overlaps replica-gradient synchronization with attention backward. We evaluate PlaceMoE on a 32-GPU cluster and a 64-NPU cluster using Qwen3-VL and DeepSeek-V3. Experimental results show that PlaceMoE achieves up to a 6.94x speedup in A2A communication and 1.74-2.33x speedups in end-to-end training over the state-of-the-art training framework VeOmni.

cs.DC↗
arXiv2026

Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution

Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements. Existing approaches typically pursue these directions separately: some methods update model weights using self-generated experience, while others rewrite the harness that defines how an agent uses prompts, tools, context, and execution feedback. However, these approaches overlook the relationship between model weights and the agent harness. To connect these processes and ensure effective and smooth agent self-evolving, we propose Evo$^2$, a framework for weight-harness co-evolution. For harness updates, we design a unified dual-role pipeline that a single policy serves as both a Proposer, which writes harness edits, and a Reflector, which diagnoses their effects and guides revision. For weight updates, harness modifications and their execution outcomes guide the training of both the Proposer and the Reflector. We further develop EvoTIDE, a training pipeline that recovers usable trajectories through edit extraction and prefix continuation, then combines SFT with interleaved GRPO across the two roles. Extensive experiments across three coding benchmarks demonstrate that Evo$^2$ significantly outperforms existing self-evolution methods. It achieves 82.1% on Polyglot and 48.3% on SWE-bench Verified, compared with 62.6% and 41.0% for the strongest baseline, respectively. We also show that the evolved harnesses transfer to different tasks without further evolution and rank first in cross-benchmark evaluations. Our dual-role harness improvement framework is also able to extend to self-evolution with proprietary models, improving a GPT-5-mini agent's performance from 24.4% to 48.3%. These results demonstrate the applicability of the framework Evo$^2$ across domains and its broad transferability across models and tasks.

cs.CL↗
arXiv2026

Opening the Black Box of Classifier-Free Guidance via Information Bottleneck

Classifier-free guidance (CFG) is a standard technique for improving conditional generation in diffusion models, yet its activation schedule is usually selected heuristically. In practice, most existing CFG-based methods rely on a pre-defined activation policy throughout inference, while recent dynamic variants often depend on hand-designed schedules without a principled theoretical explanation of when conditional information is most useful. In order to understand how the informational relevance between conditioning inputs and the score function evolves over the course of generation, we explore when guidance should be activated from an information-theoretic perspective. In this work, we formulate the diffusion trajectory as a time-dependent information bottleneck and show that the effectiveness of conditional information is not uniform throughout sampling, but becomes significantly stronger after a critical stage characterized by a Fisher-information balance condition. Motivated by this insight, we propose a training-free dynamic CFG strategy for inference. Rather than prescribing a fixed schedule in advance, our method constructs a stochastic process from conditional and unconditional score statistics and activates guidance when the estimated guidance gain crosses a prescribed threshold. This yields an adaptive activation rule that aligns condition injection with the underlying generation dynamics, while also recovering interval-based guidance as a limiting special case. Extensive experiments across diverse architectures and tasks, demonstrate that our method is effective, robust, and broadly applicable. Beyond empirical improvements, our framework provides an interpretation of dynamic guidance methods and a principled foundation for inference-time control in conditional diffusion models.

cs.LG↗
arXiv2026

RealtimeWAM: How Fast Can I Run My World Action Model?

World Action Models (WAMs) combine visual dynamics modeling with action generation, but their high inference latency limits responsive robot control. Recent efforts accelerate inference by removing explicit future-video generation at test time, as in FastWAM, an approach that requires a specially tailored architectural design. More general caching strategies exploit feature redundancy, but redundancy alone does not capture the changing computational demands of closed-loop control. To address these challenges, we present RealtimeWAM, a general, training-free framework that coordinates parallel execution with adaptive computation for low-latency inference across diverse WAM architectures. We exploit layerwise dependencies to overlap observation processing with prediction. However, concurrent branches still compete for GPU resources, limiting the benefit of parallel execution. We therefore adapt computation throughout the pipeline through selective reuse, caching observation features in visually stable regions and reusing Transformer residuals while reserving additional refinement for small predicted adjustments. We evaluate RealtimeWAM on FastWAM and OpenWAM across RoboTwin, LIBERO, and LIBERO-Plus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM, respectively.

cs.RO↗
arXiv2026

Settling PROPm and PROPavg in Graphical Resource Allocation

We study proportional fairness in graphical resource allocation, where agents are vertices, indivisible items are edges, and each item must be allocated to one of its two endpoints. It has been proved that PROP1 orientations always exist and PROPx orientations may not, but it has remained open whether the intermediate relaxations PROPm and PROPavg (both can be satisfied without graphical constraints) can always be satisfied. In this paper, we resolve this gap. We prove that PROPm orientations always exist for goods on multigraphs and can be computed efficiently. The guarantee extends to chores and a mixture of goods and chores. In sharp contrast, we show that PROPavg orientations need not exist, even for simple graphs with binary valuations, and that deciding their existence is NP-complete. We further quantify the efficiency loss of PROPm: for goods, the price of PROPm is exactly $2$, which is one of the few settings where a constant bound on the price of fairness can be obtained. We complement these results with hardness results for welfare optimization under PROPm and for the existence of orientations that are simultaneously PROPm and Pareto optimal.

cs.GT↗
arXiv2026

Pseudospin Hall Transport Induced by Berry Curvature

Pseudospin-1 Dirac systems exhibit unique physics distinct from conventional Dirac cones, such as flat-band crossings and non-Abelian characteristics, yet their topological transport properties have remained largely untapped in passive, time-reversal-invariant settings. Here we uncover an in-plane polarity of the Berry-curvature texture in a pseudospin-1 Dirac Hamiltonian, a previously unexplored geometric degree of freedom encoded in the sign-resolved distribution of Berry curvature despite zero net Berry flux, and reveal a new mechanics where Berry curvature induce pseudospin Hall behaviors in a system. We show that the oriented coupling between this momentum-space polarity and a real-space mass gradient governs a geometric selection rule that dictates the emergence of gapless pseudospin Hall modes. By engineering the intracell couplings of a four-site planar lattice, we independently program the Berry-curvature polarity and the spatial mass gradient without altering the host lattice symmetry. Acoustic experiments directly confirm this directional selection rule: reversing the mass gradient closes or reopens the dispersive gap, while pseudospin-selective source excitation launches counterpropagating pseudospin branches along arbitrary prescribed axes. Our work establishes quantum geometric polarity as a versatile tool for reconfigurable wave routing, sensing, and high-capacity quantum applications.

cond-mat.mes-hall↗
arXiv2026

PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological reasoning. We introduce PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcement signals. Although trained only on forward perturbation-response prediction, PertMind improves response inference in unseen cellular contexts while retaining general language capabilities. It also transfers, without task-specific post-training, to reverse perturbation identification, double-perturbation reasoning, phenotypic-screen prioritization, and biological-process interpretation. PertMind further generates biological profiles that support competitive gene, cell, and donor representations across multiscale downstream tasks. These results support the hypothesis that reinforcement on experimental endpoints can concentrate reusable biological strategies already accessible to pretrained models. More broadly, perturbation-derived reinforcement learning offers a scalable route for transforming expanding experimental atlases into training environments for general-purpose biological reasoning.

cs.LG↗
arXiv2026

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised graph representation learning are guided by distinct objectives and offer different perspectives on graph representations. In this work, we study whether self-supervised representations (SSL) can provide complementary signals to improve supervised OOD node classification. We develop two backbone-agnostic frameworks that exploit such information at different stages of learning and prediction. Co-Train jointly learns supervised and SSL representations and adaptively integrates them during training, while Dual-Space Retrieval performs non-parametric prediction in the two representation spaces and combines their predictions through confidence-aware fusion at inference time. The supervised and SSL encoders are separately parameterized and need not share the same GNN architecture. We evaluate multiple GNN backbones and two distinct SSL objectives, DGI and GRACE, on four graph benchmarks spanning temporal and cross-domain distribution shifts. Extensive experiments show that Co-Train consistently outperforms strong supervised OOD baselines, while Dual-Space Retrieval achieves competitive performance as a flexible non-parametric alternative. Results across different backbones and SSL objectives, together with representation analyses and ablations, demonstrate that SSL representations provide complementary information to supervised representations and can improve OOD node classification across diverse settings.

cs.LG↗
arXiv2026

GUI Agents for Continual Game Generation

Generating a game is not the same as making one playable. Existing code-generation approaches often translate a prompt directly into an artifact, leaving interaction-level failures undetected. We argue that game generation requires a player and study two roles for graphical user interface (GUI) agents. First, we introduce \textbf{PlaytestArena}, an evaluation environment containing 200 browser-based game-generation tasks across eight genres, each paired with rubrics of expected in-play behaviors. An independent GUI judge loads and plays each build to adjudicate these rubrics. Second, we propose \textbf{Play2Code}, in which a game agent and a rubric-blind GUI playtester iteratively generate, play, and refine games through shared memory. The playtester provides gameplay traces and actionable feedback, while a separate GPT-5.5 judge assigns final benchmark scores. Across three frontier backbones, Play2Code achieves a 66.8\% rubric pass rate, outperforming single-pass and agentic-coding baselines by 37.1 and 14.6 points, respectively. Its scores also improve monotonically across refinement rounds. Further analysis shows that GUI-agent feedback is fully logged and traceable, while its priorities vary substantially across model backbones. These results establish GUI playtesting as an evaluation and refinement signal for interactive code generation. Our project website is available at https://continual-game-generation.vercel.app/

cs.SE↗
arXiv2026

Do ResNets Route? Sparse Interaction Experts in Residual Networks

Residual networks execute every block for every input, yet their functional contributions need not be input independent. We formulate a trained ResNet as a set function over binary residual-branch masks and apply Möbius inversion to decompose its output exactly into individual residual corrections and higher-order interactions. For smooth residual stacks, we show that each fixed $k$-way interaction scales as $\mathcal{O}(λ^k)$ under residual scaling. Exhaustive analysis of ImageNet-pretrained ResNet-18 and ResNet-34 reveals that interaction mass peaks at orders five and ten, respectively, rather than at low orders. Reducing the residual scale shifts both spectra toward lower orders, but also changes model predictions. The interaction coefficients are concentrated in magnitude but not hard sparse, and prediction-preserving sparsity weakens with depth. Crucially, the dominant interactions vary across inputs and predicted classes around a shared global core, while their overall complexity changes little with sample difficulty. These results show that dense ResNets implement an implicit form of soft routing: every block is executed, but different inputs rely on different residual interaction experts. Routing can therefore emerge at the level of functional contribution without an explicit router or sparse execution.

cs.LG↗
arXiv2026

Exact quantum algorithm for searching of multiple sets intersection

Grover's algorithm achieves a quadratic speedup for unstructured search when a global oracle for the target set is available. However, its success probability is generally below $100\%$. To overcome this issue, Long presented a modified version of Grover's search algorithm by introducing a phase-matching condition, which can search for the target set with zero theoretical failure rate. Nevertheless, in many applications, the target set is determined by the intersection of multiple constrained sets. Most existing Grover-based methods are limited to the intersection of only two sets and are not always successful in searching for the target set. In this work, based on Long's method, we propose an algorithm for exactly searching the intersection of multiple sets. We derive and prove a phase-matching condition for searching the intersection exactly. Furthermore, we present a quantum circuit that implements exact intersection search. Finally, we support our theoretical results with numerical simulations.

quant-ph↗
arXiv2026

One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, attackers can distribute their intent across multiple benign-looking turns, making defense a problem not only of whether a dialogue is harmful, but also of when intervention becomes necessary. Existing trace-level labeling approaches provide only coarse safety signals and do not identify this intervention boundary, making it difficult to distinguish timely intervention from premature refusal or a block that comes too late. This work introduces turn-level harm-enabling supervision for multi-turn defense. We define the earliest harm-enabling turn as the first point at which delivering a candidate response would make the accumulated interaction sufficient to enable harmful action. To instantiate this supervision at scale, we construct the Multi-Turn Intent Dataset (MTID), which contains adaptive attack rollouts, matched benign hard negatives, and annotations of this boundary. Using MTID, we train TurnGate, a response-aware monitor that learns when to intervene, and further optimize its policy through multi-turn reinforcement learning. Experiments show that turn-level boundary supervision improves intervention localization, while reinforcement learning further improves the safety--utility trade-off. TurnGate outperforms existing guardrails and multi-turn monitoring baselines, and generalizes across risk domains, attacker pipelines, and target models. Our code is available at https://github.com/Graph-COM/TurnGate.

cs.CL↗
arXiv2026

See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology

Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pathology interpretation, yet their ability to perceive these details remains inadequate. This weakness leads to inaccurate cellular observations that can persist even when final answers are correct. In this paper, we propose ASPECT to improve visually grounded reasoning through explicit supervision of cellular appearance and abundance. ASPECT trains intermediate visual tokens through pathology feature reconstruction, cell feature alignment, and count supervision. Three-stage supervised fine-tuning teaches the model to perceive, generate visual tokens, and reason, followed by reinforcement learning that rewards answer correctness and consistency with reported measurements. We also introduce PathoVernier, a benchmark of 759 expert-reviewed questions from five pathology datasets covering four cellular composition tasks. It evaluates both final answers and intermediate measurements to expose errors hidden by answer accuracy. On PathoVernier, ASPECT achieves relative accuracy gains of approximately 19.2% over the strongest baseline, Gemini-3.1-Pro, and 99.3% over its Qwen3-VL-8B backbone, while reducing RAWR, which measures counting errors within correct responses, by 28.1% and 42.7%, respectively. ASPECT also improves over its backbone on three external pathology benchmarks covering classification and question answering beyond cellular composition tasks.

cs.CV↗
arXiv2026

Just Ramp-up: Debiasing Regression-based Estimator for A/B Tests under Network Interference

Network interference complicates A/B testing on online platforms, such as social networks and marketplaces, where causal methods based on single experiments often suffer from significant bias due to complex interference patterns. This paper demonstrates the statistical benefits of merging data from multiple experiments with varying treatment proportions. Sequential experimentation with increasing traffic, or ramp-up, is widely used in tech companies for risk management and cost control. Beyond operational benefits, we show that regression-based estimators trained on merged data achieve substantial bias reduction, even under simple randomization schemes and regression models. We focus on the global average treatment effect (GATE), a key estimand in the tech industry, and consider a general interference pattern that extends beyond the 1-hop setting. We present a closed-form bias variance analysis of the linear regression estimator and show that, in practical settings, the bias term dominates. Moreover, we characterize how merging data across ramp-up stages improves regression training and reduces bias. We also offer an intuitive explanation for this reduction and highlight the synergy between cluster-level randomization and our approach. Furthermore, we consider a refined estimator based on graph neural networks (GNN). Extensive simulations across challenging scenarios confirm that our methodology significantly improves the accuracy of regression-based estimators.

stat.ME↗