Searcharxiv⌕ Search

arXiv subjects

Quanming Yao

Publications and source records attributed to Quanming Yao.

At least 19 recordsLinked to original sources
arXiv2026

RuleMem: Active Rule Memory for Long-Term Conversational Agents

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to semantic gaps and unreliable reasoning. To address this limitation, we propose RuleMem, a rule-based memory framework that induces reusable logical rules from historical interactions to \textit{actively} guide both evidence retrieval and reasoning. Specifically, RuleMem constructs natural-language Horn clauses from conversations and validates them via a Rule Perplexity Consistency (RPC) mechanism. These induced rules enable the retrieval of semantically distant evidence while providing an explicit logical structure for answer generation. We conducted a comprehensive evaluation of RuleMem on two long-term conversational benchmarks, LoCoMo and LongMemEval_s*. In a rigorous comparison against 14 baselines on LoCoMo, RuleMem achieved the highest accuracy, exceeding the baseline average by 27.47 points (a 54.3% relative improvement).

cs.CL↗
arXiv2026

Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space

Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practically important as it reduces memory and inference cost for storage and deployment. Under this constraint, adaptation becomes an optimization problem over quantization codes and scales. Existing continuous low-bit training is efficient, but it can be distorted by straight through estimation error or by post-quantize gap; discrete search is deployment-faithful, but it is often too inefficient under a finite training budget. We propose code surrogate gradient as the first order signal in deployable code space to acceleate optimization, and performing guided search to preserve deployment faithfulness. Experiments across arithmetic reasoning, instruction following, and structured language understanding show that GradCodes consistently improves fine-tuning low-bit models across different quantization datatypes. Code is provided at https://github.com/ovo67/GradCodes.

cs.LG↗
arXiv2026

TAGR: Temporally Adaptive Generative Recommendation for Industrial Live-Streaming Advertising

Live-streaming advertising is an important monetization channel on short-video and e-commerce platforms, where rapidly changing live content, promoted products, and user feedback impose strong freshness requirements on recommendation models. Existing generative recommenders designed for static domains fail at three levels: static semantic IDs (SID) cannot track evolving live ads; single-scale behavior modeling misses shifting intent; preference optimization conflicts between fresh on-policy feedback and training stability. We propose TAGR, a generative recommendation framework with temporal adaptation at three levels: live-ad tokenization, user intent modeling, and preference alignment. At the token level, Live Semantic-Collaborative ID (LSID) periodically refreshes each active ad's SID based on its current live scene and promoted products, while retaining a stable hierarchical token vocabulary for autoregressive generation. At the intent level, Intent-Aware Generation (IAG) models live-room entry histories at multiple temporal granularities as the primary intent sequence, keeps auxiliary behaviors as separate inputs, and weights next-token prediction (NTP) using post-request intent evidence and business value. At the alignment level, Intermittent On-Policy Preference Optimization (IOPO) periodically samples fresh candidate groups from the current policy and performs behavior- and value-aligned preference updates interleaved with supervised NTP maintenance to preserve learned behavior distribution. Deployed on a large-scale e-commerce live-stream advertising platform, TAGR improves live-room entry and shopping-cart click rates by 8.5% and 7.4%, respectively, and achieves a 16.1% revenue lift over the production baseline. These results demonstrate the effectiveness and industrial viability of temporally adaptive generative recommendation for live-stream advertising.

cs.IR↗
arXiv2026

Falsifiable Commitment Planning for Self-Correcting Web Agents

Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, or plan assumption no longer supports the user instruction. Existing agents can plan, reflect, or reuse experience, but their plans rarely specify the evidence under which an active step should still be trusted. We propose FCPAgent, a falsifiable commitment planning framework for robust long-horizon web agents. FCPAgent represents each plan step as a Falsifiable Commitment Unit (FCU): a subgoal grounded in a reusable skill, together with confirming evidence, falsifying evidence, and a confidence score. Execution is organized as a plan-test-repair loop. The hybrid commitment testing module checks candidate actions before they modify the browser and checks observations after execution; for efficiency, it combines lightweight evidence matching with LLM-based diagnostic verification. When evidence falsifies a commitment, scope-aware repair localizes the contradiction to the execution, skill, or planning level and revises the smallest adequate part. On WebArena, FCPAgent achieves a 13.8% relative improvement in average success over the strongest baseline, with especially large gains on long-horizon tasks.

cs.AI↗
arXiv2026

Mechanistic Attention Guidance for Agent Memory Refinement

Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections. However, this text-based paradigm rarely incorporates internal mechanistic signals, leaving how retrieved memory is actually utilized during task execution underexplored. This limitation can lead to unreliable error attribution and hallucinated memory modifications. In this work, we show that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization. By aggregating attention over memory segments and decision steps, we construct a context utilization matrix that exposes recurring memory-use patterns and indicates corresponding refinement strategies. Building on this observation, we propose Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates. AGMR corrects or enhances memory for failed executions, simplifies memory for successful executions, and verifies each update through re-execution. Experiments on interactive decision-making benchmarks show that AGMR improves both task performance and memory efficiency over text-only memory refinement baselines. Code is available at https://anonymous.4open.science/r/AGMR_code-3262/

cs.AI↗
arXiv2026

DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction

Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms. We propose DDIAgents, a mechanism-conditioned multi-agent framework that performs DDI prediction through dynamic knowledge orchestration. Given a drug pair, a planner agent instantiates specialized expert agents, routes mechanism-relevant knowledge sources to each agent, and aggregates their analyses through a conclusion agent. By adapting context flow to the inferred interaction mechanism, DDIAgents reduces irrelevant information, supports complementary expert reasoning, and produces interpretable agent-level rationales. Extensive experiments on realistic DDI prediction benchmarks show that DDIAgents consistently outperforms existing feature-based, graph-based, LLM-based, and agent-based baselines. Beyond prediction performance, DDIAgents demonstrates how multi-agent systems can organize heterogeneous scientific knowledge for adaptive and interpretable AI4Science reasoning.

cs.AI↗
arXiv2026

ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents

Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become stronger, the main bottleneck shifts from local skill execution to maintaining a coherent task frontier across planning, monitoring, memory, and execution. We study task-state misalignment, a task-level consistency failure in which the planner's active stage, runtime evidence, remembered context, and delegated executor no longer justify the same next-step decision. This failure can lead to unsupported handoffs, stage lock, executor-context mismatch, and unnecessary replanning. We propose ContextFlow, an inspectable alignment framework that represents stages as explicit contracts, converts runtime observations into evidence packets, and applies scoped updates including continue, refine, transfer, promote, and repair. ContextFlow keeps specialist executors responsible for local closed-loop control while making task-frontier alignment explicit and auditable. Experiments and demonstration traces on long-horizon embodied tasks illustrate how evidence-grounded scoped updates diagnose and mitigate recurring task-state failures.

cs.RO↗
arXiv2026

Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers

Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forward pass, yet in pre-norm Transformers, large residual-stream norms play only an indirect forward role because sublayers operate on normalized inputs. We study this relationship from the perspective of backpropagation. Empirically and theoretically, we show that under causal masking, attention sinks can induce pronounced gradient concentration, which we term gradient sinks. Since the RMSNorm Jacobian attenuates gradients roughly in inverse proportion to input norm, massive activations can be understood as adaptive regulators of this localized gradient pressure during training. This interpretation predicts that attenuating sink-induced gradients should weaken massive activations. We test this prediction with V-scale, a modification that adjusts backpropagated gradients on the value path. In V-scale models, attention sinks are preserved, whereas massive activations are suppressed. These results identify gradient sinks as a backward-pass counterpart of attention sinks, and massive activations as an adaptive RMSNorm-mediated response that attenuates the resulting localized training pressure. Our code is available at https://anonymous.4open.science/r/GradientSinkCode-B309.

cs.LG↗
arXiv2026

Searching Meta Reasoning Skeleton to Guide LLM Reasoning

Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to improve reasoning performance. However, prior researches implement meta reasoning skeleton with manually designed structure, limiting ability to adapt to query-specific requirement and capture intricate logical dependency among reasoning steps. To deal with the challenges, we represent meta reasoning skeleton with directed acyclic graph (DAG) to unify skeletons proposed in prior works and model intricate logical dependency. Then we propose AutoMR, a framework that searches for query-aware meta reasoning skeleton automatically inspired by automated machine learning (AutoML). Specifically, we construct search space based on DAG representation of skeleton and then formulate the search problem. We design a dynamic skeleton sampling algorithm by expanding meta reasoning skeleton along with reasoning context at inference time. This algorithm can derive any meta reasoning skeleton in search space efficiently and adapt skeleton to evolving base reasoning context, thus enable efficient query-aware skeleton search. We conduct experiments on extensive benchmark datasets. Experimental results show that AutoMR achieves better reasoning performance than previous works broadly.

cs.AI↗
arXiv2026

PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent

Smartphone GUI agents execute tasks by operating directly on app interfaces, offering a path to broad capability without deep system integration. However, real-world smartphone use is highly personalized: users adopt diverse workflows and preferences, challenging agents to deliver customized assistance rather than generic solutions. Existing GUI agent benchmarks cannot adequately capture this personalization dimension due to sparse user-specific data and the lack of fine-grained evaluation metrics. To address this gap, we present PSPA-Bench, the benchmark dedicated to evaluating personalization in smartphone GUI agents. PSPA-Bench comprises over 12,855 personalized instructions aligned with real-world user behaviors across 10 representative daily-use scenarios and 22 mobile apps, and introduces a structure-aware process evaluation method that measures agents' personalized capabilities at a fine-grained level. Through PSPA-Bench, we benchmark 11 state-of-the-art GUI agents. Results reveal that current methods perform poorly under personalized settings, with even the strongest agent achieving limited success. Our analysis further highlights three directions for advancing personalized GUI agents: (1) reasoning-oriented models consistently outperform general LLMs, (2) perception remains a simple yet critical capability, and (3) reflection and long-term memory mechanisms are key to improving adaptation. Together, these findings establish PSPA-Bench as a foundation for systematic study and future progress in personalized GUI agents.

cs.AI↗
arXiv2026

DGNet: Discrete Green Networks for Data-Efficient Learning of Spatiotemporal PDEs

Spatiotemporal partial differential equations (PDEs) underpin a wide range of scientific and engineering applications. Neural PDE solvers offer a promising alternative to classical numerical methods. However, existing approaches typically require large numbers of training trajectories, while high-fidelity PDE data are expensive to generate. Under limited data, their performance degrades substantially, highlighting their low data efficiency. A key reason is that PDE dynamics embody strong structural inductive biases that are not explicitly encoded in neural architectures, forcing models to learn fundamental physical structure from data. A particularly salient manifestation of this inefficiency is poor generalization to unseen source terms. In this work, we revisit Green's function theory-a cornerstone of PDE theory-as a principled source of structural inductive bias for PDE learning. Based on this insight, we propose DGNet, a discrete Green network for data-efficient learning of spatiotemporal PDEs. The key idea is to transform the Green's function into a graph-based discrete formulation, and embed the superposition principle into the hybrid physics-neural architecture, which reduces the burden of learning physical priors from data, thereby improving sample efficiency. Across diverse spatiotemporal PDE scenarios, DGNet consistently achieves state-of-the-art accuracy using only tens of training trajectories. Moreover, it exhibits robust zero-shot generalization to unseen source terms, serving as a stress test that highlights its data-efficient structural design.

cs.LG↗
arXiv2026

MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems

Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness.

cs.MA↗
arXiv2026

DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation

Owing to their unprecedented comprehension capabilities, large language models (LLMs) have become indispensable components of modern web search engines. From a technical perspective, this integration represents retrieval-augmented generation (RAG), which enhances LLMs by grounding them in external knowledge bases. A prevalent technical approach in this context is graph-based RAG (G-RAG). However, current G-RAG methodologies frequently underutilize graph topology, predominantly focusing on low-order structures or pre-computed static communities. This limitation affects their effectiveness in addressing dynamic and complex queries. Thus, we propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically. DA-RAG captures high-order graph structures, allowing for the retrieval of self-complementary knowledge. Furthermore, DA-RAG is equipped with a chunk-layer oriented graph index, which facilitates efficient multi-granularity retrieval while significantly reducing both computational and economic costs. We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons across four metrics while reducing index construction time and token overhead by up to 37% and 41%, respectively.

cs.IR↗
arXiv2026

Self-Generative Adversarial Fine-Tuning for Large Language Models

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent self-play and synthetic data approaches reduce this dependence but often rely on heuristic assumptions or ungrounded self-evaluation, which can cause bias accumulation and performance drift. In this paper, we propose Self-Generative Adversarial LLM (SGALM), a unified fine-tuning framework that formulates alignment as a generative adversarial game within a single LLM. SGALM jointly evolves generation and discrimination capabilities without external reward models. Theoretical and empirical results demonstrate that SGALM achieves state-of-the-art performance, serves as an effective alignment algorithm and a robust synthetic data engine.

cs.LG↗
arXiv2026

Scaling GraphLLM with Bilevel-Optimized Sparse Querying

LLMs have recently shown strong potential in enhancing node-level tasks on text-attributed graphs (TAGs) by providing explanation features. However, their practical use is severely limited by the high computational and monetary cost of repeated LLM queries. To illustrate, naively generating explanations for all nodes on a medium-sized benchmark like Photo (48k nodes) using a representative method (e.g., TAPE) would consume days of processing time. In this paper, we propose Bilevel-Optimized Sparse Querying (BOSQ), a general framework that selectively leverages LLM-derived explanation features to enhance performance on node-level tasks on TAGs. We design an adaptive sparse querying strategy that selectively decides when to invoke LLMs, avoiding redundant or low-gain queries and significantly reducing computation overhead. Extensive experiments on six real-world TAG datasets involving two types of node-level tasks demonstrate that BOSQ runs substantially faster than existing GraphLLM methods while consistently delivering on-par or superior performance.

cs.DB↗
arXiv2026

Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning

Temporal knowledge graph reasoning (TKGR) aims to predict future events by inferring missing entities with dynamic knowledge structures. Existing LLM-based reasoning methods prioritize contextual over structural relations, struggling to extract relevant subgraphs from dynamic graphs. This limits structural information understanding, leading to unstructured, hallucination-prone inferences especially with temporal inconsistencies. To address this problem, we propose IGETR (Integration of Graph and Editing-enhanced Temporal Reasoning), a hybrid reasoning framework that combines the structured temporal modeling capabilities of Graph Neural Networks (GNNs) with the contextual understanding of LLMs. IGETR operates through a three-stage pipeline. The first stage aims to ground the reasoning process in the actual data by identifying structurally and temporally coherent candidate paths through a temporal GNN, ensuring that inference starts from reliable graph-based evidence. The second stage introduces LLM-guided path editing to address logical and semantic inconsistencies, leveraging external knowledge to refine and enhance the initial paths. The final stage focuses on integrating the refined reasoning paths to produce predictions that are both accurate and interpretable. Experiments on standard TKG benchmarks show that IGETR achieves state-of-the-art performance, outperforming strong baselines with relative improvements of up to 5.6% on Hits@1 and 8.1% on Hits@3 on the challenging ICEWS datasets. Additionally, we execute ablation studies and additional analyses confirm the effectiveness of each component.

cs.LG↗
arXiv2025

LLM-Empowered Representation Learning for Emerging Item Recommendation

In this work, we tackle the challenge of recommending emerging items, whose interactions gradually accumulate over time. Existing methods often overlook this dynamic process, typically assuming that emerging items have few or even no historical interactions. Such an assumption oversimplifies the problem, as a good model must preserve the uniqueness of emerging items while leveraging their shared patterns with established ones. To address this challenge, we propose EmerFlow, a novel LLM-empowered representation learning framework that generates distinctive embeddings for emerging items. It first enriches the raw features of emerging items through LLM reasoning, then aligns these representations with the embedding space of the existing recommendation model. Finally, new interactions are incorporated through meta-learning to refine the embeddings. This enables EmerFlow to learn expressive embeddings for emerging items from only limited interactions. Extensive experiments across diverse domains, including movies and pharmaceuticals, show that EmerFlow consistently outperforms existing methods.

cs.AI↗
arXiv2025

Evolutionary Discovery of Heuristic Policies for Traffic Signal Control

Traffic Signal Control (TSC) involves a challenging trade-off: classic heuristics are efficient but oversimplified, while Deep Reinforcement Learning (DRL) achieves high performance yet suffers from poor generalization and opaque policies. Online Large Language Models (LLMs) provide general reasoning but incur high latency and lack environment-specific optimization. To address these issues, we propose Temporal Policy Evolution for Traffic (\textbf{\method{}}), which uses LLMs as an evolution engine to derive specialized heuristic policies. The framework introduces two key modules: (1) Structured State Abstraction (SSA), converting high-dimensional traffic data into temporal-logical facts for reasoning; and (2) Credit Assignment Feedback (CAF), tracing flawed micro-decisions to poor macro-outcomes for targeted critique. Operating entirely at the prompt level without training, \method{} yields lightweight, robust policies optimized for specific traffic environments, outperforming both heuristics and online LLM actors.

cs.AI↗