Search arXiv⌕ Search

arXiv subjects

Bo Tang

Publications and source records attributed to Bo Tang.

At least 19 recordsLinked to original sources
arXiv2026

ISAC-Assisted Proactive Handover in mmWave Networks: Value of Foresight and Localization Requirements

Millimeter-wave (mmWave) links can lose tens of decibels within milliseconds when a person or vehicle crosses the line of sight, and reactive handover recovers only after the outage has begun. Integrated sensing and communication (ISAC) promises to let the network see blockers coming and move users to another cell in advance. This paper asks how much such foresight is worth relative to the best reactive handover, and what sensing accuracy is needed to harvest it. We formulate cost-aware cell selection with knowledge of the future signal-to- noise ratio as a sequential decision problem, define the value of foresight through a policy-independent bound, and develop an ISAC-assisted handover framework in which a radio unit senses blockers with its own communication waveform and a simulated Open RAN xApp plans handovers. Ray-traced experiments in a 28 GHz street canyon, reported on held-out scenarios, show that, with a short look-ahead, perfect foresight closes most of the gap between service-aware (Layer-3) reactive handover and an instantaneous oracle. Harvesting this value, however, requires the user and nearby blockers to be localized to about a decimeter, well beyond what our radar tracker and meter- level user positioning provide; with realistic errors, even an uncertainty-aware planner largely defers to reactive handover.

eess.SY↗
arXiv2026

Sense Less, Miss Less: Evidence-Driven Sensing Schedules for ISAC

Integrated sensing and communication (ISAC) lets a base station detect human motion with the same signals it uses for data, but every sensing transmission takes resources from users. Sensing rarely while nothing moves saves resources, yet a brief hand gesture by an otherwise still person can then start and end between two transmissions and go unnoticed. We propose an evidence-driven schedule, based on data-efficient cumulative-sum (CuSum) change detection, that pauses sensing while measurements indicate no motion and senses continuously once they suggest motion. It is adapted to orthogonal frequency-division multiplexing (OFDM) sensing, where requests can be blocked by data traffic and measurements arrive late, and evaluated with an articulated human model of limb motion. In simulations without wall reflections, with the same monitoring budget and below one false alarm per minute, it detects 1.5--4.2 times as many limb movements within 200~ms as periodic sensing. A tuned two-rate trigger performs similarly, and the gain over periodic sensing persists, without retuning or cost matching, in a simulated room with wall reflections. Under a small budget, measurements should decide when to sense.

eess.SP↗
arXiv2026

mmWave UE Positioning Under Blockage: Limits for ISAC-Assisted Handover

Proactive handover can save a millimeter-wave (mmWave) link before a passing body blocks it, but only if the network knows where the user is. We ask whether the radio units that serve a user can localize it accurately enough from its uplink sounding reference signals. We derive position error bounds that include synchronization and array calibration errors, with and without reflected paths known from a digital twin, and test two estimators in a ray-traced street canyon on held-out scenarios. Three findings stand out. First, with line of sight to both radio units, array calibration, not bandwidth, limits the bound. Second, blockage degrades the line-of-sight-only bound sharply, whereas known reflections keep the map-aided bound low. Third, a simple dominant-path estimator fails where it matters most: its errors grow sharply around blockage, and proactive handover becomes worse than the 3GPP baseline. A map-aided multipath tracker cuts the median error from 12 to 3.7 cm and removes this significant penalty at link margins of 15 dB and above, but does not yet beat the baseline.

cs.NI↗
arXiv2026

Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG

Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is one such setting: at each frontier of a document tree, an LLM commits to $b$ of $k$ sections under an input-dependent action grammar, executed as either failure-prone free-form JSON or reliable but strictly serial grammar-constrained generation. We show that this serialization is unnecessary for bounded-horizon control: the reachable future forms a shallow action-prefix tree, which we compile --- one root prefill plus one tree-causal probe evaluate every prefix-conditioned action distribution with serial decoding's tokens, positions, and causal ancestry. A prefix-state lemma makes compiled control policy-exact in exact arithmetic: the same policy with a two-forward critical path and zero output tokens. One further probe pass certifies the exact order-marginalized MAP set. Across four document-disjoint splits and two scales on the primary MetaX device, compiled control matches the serial policy on $84$--$89\%$ of questions --- every instrumented divergence a floating-point near-tie --- and cuts control latency by $35$--$47\%$ versus token-wise serial decoding and $6$--$7\%$ versus an idealized chunked engine; an H800 repetition preserves the ordering.

cs.CL↗
arXiv2026

MemT-1.0: Towards Memory-Native Evolution

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.

cs.CL↗
arXiv2026

FairShare: Auditable Geographic Fairness for Multi-Operator LEO Spectrum Sharing

Dynamic spectrum sharing (DSS) among multi-operator low Earth orbit (LEO) mega-constellations is essential for coexistence, yet prevailing policies focus almost exclusively on interference mitigation, leaving geographic equity largely unaddressed. This work investigates whether conventional DSS approaches inadvertently exacerbate the rural digital divide. Incorporating Keplerian orbital dynamics, inter-beam co-channel interference, and three real-world constellation geometries (Starlink, OneWeb, Kuiper), we conduct large-scale, 3GPP-compliant non-terrestrial network (NTN) simulations across 20 orbital snapshots spanning 10~minutes of satellite motion. The results uncover a stark and persistent structural bias: SNR-priority scheduling induces a $1.84\times$ mean urban--rural access disparity, with temporal fluctuations reaching $3.9\times$ during favorable interference conditions. Counter-intuitively, increasing system bandwidth amplifies rather than alleviates this gap. To remedy this, we propose FairShare, a lightweight, quota-based framework that enforces geographic fairness. FairShare not only reverses the bias, achieving an affirmative disparity ratio of $Δ_{\text{geo}} = 0.68\times$ with zero variance across all orbital snapshots and interference conditions, but also reduces scheduler runtime by 3.3\%. This demonstrates that algorithmic fairness can be achieved without trading off efficiency or complexity, and that it remains invariant to physical-layer dynamics. Our work provides regulators with both a diagnostic metric for auditing fairness and a practical, enforceable mechanism for equitable spectrum governance in next-generation satellite networks.

cs.NI↗
arXiv2026

Provable Transformer Context Compression for In-Context Reinforcement Learning

Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context sizes that grow with the number of sampled transitions, leading to increasing memory costs in large-scale problems. This raises a fundamental scalability question: how much context is intrinsically necessary to carry out such learning? We answer this question for fixed-policy TD evaluation. We show that, with a shared linear decoder, the minimum context dimension required to exactly reproduce the first $L$ TD iterates is the Krylov dimension induced by the sampled transitions. When the available context dimension $m$ falls below this threshold, exact reproduction is no longer possible. In this regime, we characterize the optimal approximation error and show that it decays as $Θ(γ^m\max\{1,1/(m(1-γ))\})$ where $γ$ is the discounting factor. Moving from representation complexity to actual memory cost, we characterize the optimal retained memory for exact continuous representations as $Θ(nk_L)$ and show experimentally that on a sampled task whose exact rank is full but whose numerical rank is small, a context accurate to $10^{-2}$ is $88.7\%$ smaller than the sparse sufficient statistics of TD. Finally, we establish the learnability of the shared executor through pretraining by proving global convergence of an auxiliary objective over effective attention parameters under suitable task diversity. Experiments across diverse TD evaluation problems validate parameter recovery and the predicted context--accuracy tradeoff.

cs.LG↗
arXiv2026

H-PDLP: GPU-Accelerated Linear Programming via Generalized PDHG and Homogeneous Self-Dual Embedding

GPU-based first-order methods are emerging as an approach for solving large-scale linear programming (LP) problems. We present H-PDLP, a GPU first-order LP solver based on a generalized primal-dual hybrid gradient (PDHG) method for a homogeneous self-dual embedding of the LP, and study its numerical performance. The solver applies the restarted reflected Halpern iteration to the generalized PDHG operator, with the embedding encoding both primal-dual optimal solutions and certificates of primal or dual infeasibility. We derive a compact embedding for LPs with two-sided constraint and variable bounds in which the bounds enter through box cones, and we show that the resulting box-cone projections reduce to one-dimensional root-finding problems, so that each iteration remains matrix-free and well suited to GPUs. On the theoretical side, we establish conditions under which the iterates remain uniformly bounded away from the trivial zero solution of the embedding and derive complexity guarantees for the method. We also introduce MIPLIBInfeas, a reproducible benchmark of 229 infeasible and 105 unbounded LPs derived from MIPLIB 2017. Numerical experiments demonstrate the effectiveness of the proposed approach on both feasible LPs and infeasible or unbounded LPs. The source code for H-PDLP is publicly available at https://github.com/MIT-Lu-Lab/H-PDLP.

math.OC↗
arXiv2026

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation without accounting for the dependency chains through which memories enable the creation of future memories. We introduce MemQ, which applies TD($λ$) eligibility traces to memory Q-values, propagating credit backward through a provenance DAG that records which memories were retrieved when each new memory was created. Credit weight decays as $(γλ)^d$ with DAG depth $d$, replacing temporal distance with structural proximity. We formalize this setting as an Exogenous-Context MDP, separating externally supplied tasks from the evolving memory store, and represent retrieval-set values by a first-order mean of per-memory values plus an explicit approximation residual. Across five interaction, code-generation, and agentic benchmarks, MemQ improves average held-out, final runtime, and cumulative success rates over the baseline with the highest average for each metric by 2.53, 4.23, and 2.13 percentage points, respectively. Ablations on LiveCodeBench, BFCL, and DSBench support the benefit of bootstrapping and multi-depth credit propagation. Analyses of Q-values and runtime learning show that learned memory values are associated with subsequent success and that MemQ retains more of its historical task coverage. We also explore the limits of MemQ's benefits using multiple-choice reasoning tasks, where limited interaction offers fewer opportunities to reuse procedural experience. Code is available at https://github.com/jwliao-ai/MemQ.

cs.AI↗
arXiv2026

MemTrace: State-Consistent Memory for Long-Horizon Coding Agents

As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these challenges through techniques like larger context windows, compression, retrieval, or repository representations, but often fail to reconstruct a consistent task state after a context refresh or verify whether recalled evidence remains valid. Thus, we introduce MemTrace, a provenance-aware memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state. MemTrace stores history as immutable Memory Traces anchored to key information (e.g., files, symbols, tests), and organizes their execution order and dependencies in a Memory Trace Graph. When context is constrained, working memory retains only compact Memory Anchors, from which the agent can reconstruct the latest execution state and locate evidence relevant to its next action. Before restoring historical evidence, MemTrace checks its validity against the current repository state and retrieves only what the next action requires. Across three complementary long-horizon coding benchmarks, MemTrace consistently outperforms all fully evaluated baselines under the same backbone and harness, improving DeepSWE pass@1 by 21.2 points, SWE-EVO Resolved Rate by 4.4 points, and SWE-Milestone Score by 17.8 points under Codex CLI.

cs.AI↗
arXiv2026

MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems

LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gives attackers a durable channel: a poisoned memory can be written once, continuously retrieved in later tasks, promoted into shared memory, and reused by other agents. A single poisoned write can therefore steer many later decisions and contaminate agents that never saw the original attack, all while no malicious message crosses a visible communication edge at the moment of harm. Further, because existing safeguards mainly inspect prompts, actions, or communication edges, they can miss attacks whose content appears benign at write time but becomes harmful after retrieval. We introduce Memory-Aware Propagation and Link Enforcement Guard, MAPLE-Guard, a memory-link guard for memory-enabled MAS. MAPLE-Guard monitors the memory lifecycle and places gates at write, retrieval, promotion, and cross-agent reuse, so risky memories can be quarantined, unsafe retrievals filtered, and poisoned private memories blocked before they enter shared memory. In the main evaluation, MAPLE-Guard lowers attack success rate (ASR) from 38.2% to 0.9% on LongMemEval and from 34.7% to 0.2% on AppWorld; it also raises multi-agent defense success rate (MDSR) from 54.0% to 74.3% and from 42.5% to 99.8% on the same benchmarks. These results suggest that memory-aware link enforcement covers a gap left by prompt-level and topology-level defenses. Code is available at the link: https://github.com/xiong-wenjun/MAPLE-Guard.

cs.MA↗
arXiv2026

On the origin of carbon- and oxygen-rich hot subdwarfs: an sdB merger scenario

Carbon- and oxygen-rich hot subdwarfs (CO-sdO stars) represent an extremely rare subclass of helium-rich hot subdwarfs. Recent observations of PG 1654+322, PG 1528+025, and UCAC4 108 reveal unusually large surface mass fractions of carbon and oxygen, which are difficult to explain within existing formation scenarios. We explore whether mergers involving sdB stars can provide a viable formation channel for these objects. Using the stellar evolution code MESA, we model the post-merger evolution of two merger channels: mergers between two sdB stars and mergers between a helium white dwarf and an sdB star. Carbon and oxygen synthesized during core helium burning in sdB stars may provide a natural chemical reservoir if efficient mixing occurs during the merger. The resulting evolutionary tracks are broadly consistent with the effective temperatures, surface gravities, and luminosities observed for the three stars, suggesting remnant masses of about 0.8-1.0 M_sun. Our calculations suggest that mergers involving sdB stars may represent a viable formation pathway for CO-rich hot subdwarfs.

astro-ph.SR↗
arXiv2026

TRACE: Governing Memory Validity in Evolving Multi-Agent Systems

Persistent memory lets language-model agents carry information across long-running collaborations, but leaves a lifecycle question open: what may a returning agent still act on once the shared state has changed? A memory can be correctly retrieved, relevant to the current task, and faithful to its source, and nonetheless be inadmissible for action: an itinerary saved before a pause still names the hotel the team has since replaced. We formalize this as temporal memory admission and present TRACE, a training-free layer that treats re-entry as an eligibility decision rather than a storage or retrieval operation, reconciling a departure checkpoint against absence-period updates, resolving explicit and implicit invalidation, and releasing a bounded Return View only when it covers the returning role's open obligations. We evaluate TRACE under three actor models on Memora, STALE Type II, and a derived ManBench-Return setting, each recast as return episodes: one agent departs, four teammates change the shared state, and the agent rejoins. What separates methods is not overall accuracy but whether one can retain valid memory and reject stale memory at once, and no single-policy baseline can: Restore (reinstate the departure checkpoint in full) admits stale state, Reset (start the return from an empty memory) discards valid state, each bottoming out at 0% on one of the two. TRACE is the only method high on both, reaching 92.6-98.3% valid-information availability with 98.4-99.5% invalid-information rejection on ManBench-Return, within 3.8 points of the best baseline's overall accuracy. On STALE Type II it improves Overall over the strongest comparison policy by 22.3 (Qwen), 18.5 (Gemini), and 27.5 (DeepSeek) points at roughly 2.3 times their tokens, while a write-time consolidation pipeline is more accurate still at 3.99 times TRACE's.

cs.MA↗
arXiv2026

Noise-Robust Quantum State Characterization for Remote State Preparation with Deep Learning

Quantum communication underpins secure information processing and scalable quantum networks. In particular, remote state preparation (RSP) enables efficient quantum state transfer, but accurately estimating target states under complex noise remains challenging. Here, we propose a Transformer-based Quantum State Characterizer (TQSC) model for noisy RSP experiments. Our model reconstructs experimentally prepared pure and mixed photonic polarization states from noisy measurements in complex scattering environments, while its attention patterns provide physically grounded insights into correlations among the measured observables. The method achieves a mean estimator-target fidelity exceeding 99.999% under complex scattering and dynamic Gaussian noise, while its robustness and generalization are further examined using Qiskit-simulated Bloch-ball states. Furthermore, in a practical MNIST image transmission task with held-out states, the decoded bit error rate is reduced from 50.34% to zero after TQSC post-processing. The TQSC model enables accurate tomographic characterization under dynamic noise and provides physically grounded post-hoc insights, holding promise for intelligent quantum information processing applications.

quant-ph↗
arXiv2026

Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN

The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources. We demonstrate on a live O-RAN system that this independence is unsafe. Two agents with individually correct objectives, one protecting a latency SLA and one maximizing utilization for energy efficiency, jointly drive recurring opposing excursions of the shared resource partition that neither produces alone. Existing conflict-mitigation mechanisms presume a statically known application population and cannot govern agents whose behavior emerges at run time. We present AURA, a lightweight arbitration layer that admits agent actions only when they satisfy feasibility invariants, per-variable dwell times, and a deadband, and we prove the arbitrated system converges to a feasible operating point. Implemented on an OpenAirInterface (OAI) testbed with measured one-way latency and throughput, AURA reduces recurring shared-state excursions by more than an order of magnitude (from 8.4 to 0.4 PRB amplitude) and virtually eliminates cross-slice throughput starvation (from 40-55% to 0.3%), while leaving the protected slice's own latency compliance unchanged, a trade-off the convergence guarantee makes explicit.

cs.NI↗
arXiv2026

NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation

Real-world deployment of Vision-Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution smoothness. We present NebulaVLA, an asynchronous dual-frequency architecture that decouples high-level semantic reasoning from low-level action control, optimizing computational resources and modularity. To bridge semantic gaps across heterogeneous robots, we introduce GESTURE-7, a unified language-grounded action representation. Furthermore, our Guide Action algorithm enforces kinematic continuity via mask-based smoothness constraints. Comprehensive evaluations demonstrate that NebulaVLA significantly outperforms synchronous baselines, achieving an 85.5\% average success rate on LIBERO-Plus and accelerating action generation by \textasciitilde 2.7$\times$. This asynchronous design enables highly efficient and responsive control for practical robotics.

cs.RO↗
arXiv2026

PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue

Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically static profiles that cannot be updated locally without destabilizing unchanged traits, and benchmarks mainly test persona preservation and memory recall rather than whether a model speaks from a character's currently evolved state. We address both. PHASE-Tree is a multi-timescale character-state tree with an immutable identity root and mutable persona, session, and moment layers, making each mutable field an addressable target for localized within- and cross-episode updates. It conditions generation through explicit textual provision or implicit parametric adaptation. To measure evolved-state generation, we introduce LongEvoRoleBench, which pairs four long-dialogue corpora for cross-episode evolution with four short-dialogue corpora as within-scene state-tracking checks, under a unified next-utterance protocol. On the long-dialogue core, textual PHASE-Tree ranks first in 11 of 12 dataset-metric cells against internal variants and all 12 cells against external textual baselines, improving character-level, semantic, and embedding scores by 19.7%, 12.4%, and 15.1% respectively. In a blinded 200-response study, human ratings correlate with the GPT-4.1 judge (Pearson r= 0.65); on descriptive n= 10 PT and NR prompt subsets, the Overall difference is +0.20. The long-dialogue Sem advantage persists across LLM judges and generation backbones.

cs.CL↗
arXiv2026

Metis: Memory Foundation Model

Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is still primarily implemented through external modules, leaving the native memory capability largely unexplored. In this paper, we take a first step toward this direction by introducing memory foundation models, which empower foundation models with native memory capabilities. We formalize native memory from two perspectives: a persistent and dynamically evolving memory state within the backbone, and native memory procedures that autonomously store and utilize information through model computation. We show that native memory offers advantages in architecture, end-to-end optimization, and efficiency. Based on this formulation, we propose Metis, the first prototype of memory foundation models. Metis introduces a new architecture that equips a foundation model with a native memory state, allowing historical information to be compressed into the model and accessed through memory attention. We construct large-scale memory-specific training data and introduce multiple optimization objectives to acquire these native memory procedures through mid-training. The online memory maintenance of Metis is gradient-free, and the memory update requires only a forward pass. At inference time, all learned model weights remain frozen, while the native memory states are autonomously transformed through standard forward computation. Through extensive experiments, we show that Metis exhibits native memory capabilities and further provide a detailed analysis of its strengths, limitations, and behaviors. To facilitate future research on memory foundation models, we release our project and model checkpoints.

cs.CL↗