IJCAI 2026 论文列表

Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Recent work addresses these challenges by using custom state-space representations and metrics to compare observations against hypotheses. However, these approaches often overlook well-established encoding techniques used in other domains that offer substantial advantages. This paper introduces a novel method for online goal recognition that leverages path signatures, a compact, expressive representation of rough path theory that captures key semantic features of trajectories in an efficient way, enabling more meaningful comparisons between them. Experiments show that our method consistently outperforms the state of the art in predictive accuracy and online planning efficiency, while remaining competitive offline.

Automated temporal planning is used to synthesize courses of action for a deterministic abstraction of a system; the produced plans are often modeled as schedules of tasks to be executed on the real system under control. A key problem with adopting this architecture is how to ensure the plan is executable and goal-reaching on the real system, which can be arbitrarily complex and possibly non-deterministic. In this paper, we propose a framework to exploit task-level contracts, expressed as assumptions and guarantees at the beginning and end of tasks, to automatically synthesize plans that are guaranteed to be correct on any system satisfying the contracts. Our framework combines a temporal planner to generate candidate plans and a contract reasoner to instantiate and verify the contracts associated with the plan. If the plan is found invalid, we refine the planning problem until a valid plan is found. We present an experimental evaluation on a realistic case-study and on several synthetic problems, showing the applicability of the approach.

Partial order causal link (POCL) planning offers rich structural representations for plan optimization. However, under the classical threat definition, POCL plans form a strict subset of valid partial-order (PO) plans. This gap limits existing POCL optimization techniques to a restricted subspace of PO solutions. We revisit 'white knight' threat semantics, which permit a causal link to persist across a threat provided the deleted condition is re-established by an intermediate producer. We prove that under this definition, the POCL and PO solution spaces become equivalent. By extending a MaxSAT-based optimization framework, we demonstrate that white knights are theoretically necessary for completeness and practically advantageous: they yield plans with significantly fewer ordering constraints in domains with complex causal interference while maintaining computational tractability on standard benchmarks.

We study a robust scheduling problem on identical machines in which machines may fail after the initial assignment. The goal is to compute an initial schedule together with a recovery strategy that minimizes the post-failure makespan, under the constraint that jobs on available machines cannot be moved. We consider two failure models: a strong adversary, which selects the failed machines, and a weak adversary, which selects only the number of failures. For up to k failures, we give algorithms with robustness ratios 1.618 for the strong adversary and 1.5 for the weak adversary. For the single-failure case, k = 1, we obtain best possible ratios 1.387 and 1.281, respectively, matching our lower bounds.

Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current training paradigms suffer from a fundamental limitation: they primarily focus on next-node prediction for solution construction, resulting in myopic decision-making that undermines long-horizon planning capacity. To this end, we introduce Multi-node Lookahead Prediction (MnLP), a novel training strategy that extends the supervised learning paradigm to predict multiple future nodes simultaneously. We incorporate causal and discardable MnLP modules that operate exclusively during training, facilitating models to anticipate multi-step decisions while preserving inference-time efficiency. By incorporating multi-depth auxiliary supervision into the loss function, MnLP equips neural policies with the ability of long-range contextual understanding. Experimentally, MnLP outperforms existing training methods, improving the generalization capability of neural policies across various problem sizes, distributions, and real-world benchmarks. Moreover, MnLP can be seamlessly integrated into diverse neural architectures without introducing additional inference overhead.

Under the shift toward Industry 4.0, mass-customized manufacturing systems have introduced complex scheduling problems, such as the Flexible Job Shop Scheduling Problem (FJSSP). Recent Deep Reinforcement Learning (DRL)-based heuristics have shown promise, yet existing methods often suffer from two key limitations: they typically rely on single-policy optimization, which limits exploration, and on imprecise reward functions, which fail to accurately reflect decision quality. To address these challenges simultaneously, we propose PGMPO (Preference-Guided Multi-Policy Optimization), a novel learning framework consisting of (1) a simple but effective multi-policy modeling approach that allows a single network to represent multiple decision-makers, and (2) a preference-driven model optimization method that effectively guides policies to learn diverse and specialized problem-solving strategies without the need for explicit reward functions. Experimental results demonstrate that PGMPO substantially boosts the performance of existing neural solvers across several benchmarks.

The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimization of production goals. Conventional priority rules are insufficiently flexible to handle complex disruptions, whereas learning-based approaches often compromise interpretability or fail to generalize across problem scales. Although Large Language Models (LLMs) offer advanced reasoning capabilities to bridge this gap, their substantial inference latency is incompatible with the millisecond-level decision cycles of industrial control systems. To resolve this conflict, we introduce RACE-Sched, an asynchronous agent-based framework that decouples policy execution from logical reasoning via a dual-stream architecture. The Reactive Stream executes low-latency symbolic heuristics to enable real-time dispatching, while the parallel Deliberative Stream leverages an LLM to synthesize, validate, and evolve these rules. Candidate rules undergo rigorous testing in a sandbox and are deployed via atomic updates, ensuring safety without blocking the control loop. Additionally, a semantic rule repository indexes validated heuristics for retrieval-based initialization which enhances transferability across problem scales. Extensive evaluations on GEN-Bench, MK-Bench, and JMS-Bench demonstrate that RACE-Sched outperforms leading Deep Reinforcement Learning and other LLM-based baselines. This approach harmonizes real-time constraints with long-horizon reasoning to achieve superior solution quality and robust adaptation to dynamic events.

Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general-domain data and struggle with the structured, symbolic, and fact-sensitive nature of financial reasoning. Financial tasks require not only correct final answers but also verifiable intermediate steps grounded in domain knowledge. In this paper, we propose Fin-PRM, a domain-specialized, trajectory-aware PRM for financial reasoning that jointly models step-level correctness and trajectory-level coherence, producing binary supervision signals for both local and global reasoning quality. To support reliable supervision, we construct a high-quality financial reasoning dataset of 3K trajectories, where step- and trajectory-level labels are automatically derived from multi-source reward signals, including Monte Carlo rollouts, LLM-based evaluation, and explicit financial knowledge verification. Fin-PRM defines a unified ranking score that integrates step- and trajectory-level rewards, enabling consistent use across multiple settings. We evaluate Fin-PRM in three scenarios: (1) offline trajectory selection for supervised fine-tuning, (2) reward-guided Best-of-N inference for test-time scaling, and (3) process-aware reward shaping for reinforcement learning. Experiments on financial reasoning benchmarks, including CFLUE and FinQA, show that Fin-PRM consistently outperforms general-purpose PRMs and strong baselines. Our project resources will be available at https://github.com/aliyun/qwen-dianjin.

Retrieving real time information is a fundamental capability for agents with search capabilities in real world applications. However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information and the continuously evolving nature of real world knowledge. To address this limitation, we propose RT-QA, a dynamic evaluation framework that leverages executable code workflows to retrieve current answers at evaluation time. Specifically, we construct an agent based pipeline that autonomously generates code for web crawling and DOM based answer extraction to produce real time ground truth. To ensure robust evaluation over time, the pipeline further incorporates a repair mechanism to adapt to changes in web page structures. RT-QA spans 12 domains, such as Finance and Sports, with 320 Chinese questions categorized into three difficulty levels. Extensive evaluations of advanced models, such as GPT-5.2 and GLM-4.7, reveal significant limitations in real time adaptability: even the best models achieve only 46% accuracy. Our analysis highlights two primary failure modes: (1) Lazy Retrieval, where agents rely on search snippets instead of deeply scanning specific websites for information, accounting for 20% of failures; and (2) Temporal Confusion, a cognitive error where agents retrieve a historical date, for example an event in 2024, and fail to anchor again to the current time, 2026, for subsequent reasoning. These findings suggest that future agents require not just better retrieval strategies, but robust temporal state management.

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged as a standard practice. However, existing approaches predominantly treat teacher models as simple binary annotators, failing to fully exploit the rich knowledge and capabilities for RM distillation. To address this, we propose RM-Distiller, a framework designed to systematically exploit the multifaceted capabilities of teacher LLMs: (1) Refinement capability, which synthesizes highly correlated response pairs to create fine-grained and contrastive signals. (2) Scoring capability, which guides the RM in capturing precise preference strength via a margin-aware optimization objective. (3) Generation capability, which incorporates the teacher's generative distribution to regularize the RM to preserve its fundamental linguistic knowledge. Extensive experiments demonstrate that RM-Distiller significantly outperforms traditional distillation methods both on RM benchmarks and reinforcement learning-based alignment, proving that exploiting multifaceted teacher capabilities is critical for effective reward modeling. To the best of our knowledge, this is the first systematic research on RM distillation from generative LLMs.

Semi-supervised clustering (SSC) enables personalized clustering under limited user supervision. Given the sparsity of initial user intents, constraint propagation has been proposed as a powerful approach to explore and generate new performance-enhancing constraints. However, existing methods struggle to handle a large number of ``gray samples'' that deviate from initial supervision signals and exhibit ambiguous semantics with indistinct boundaries. Compared with ``distinct samples'' that closely match the supervision, gray samples typically contain richer latent semantics, and accurately identifying their relational types can significantly improve clustering performance. To address this challenge, we propose Adversarially Enhanced Propagation-driven Intent-aware Clustering (AEPIC). Specifically, we design an Adversarially Enhanced Constraint Propagation (AECP) mechanism that leverages global adversarial learning over dual relational links to identify gray samples and expand them into meaningful pseudo-user intents. In addition, an intent-aware regularization strategy integrates these pseudo-user intents into representation learning and clustering optimization, further improving clustering performance. Experiments on 5 benchmark datasets demonstrate that, under sparse supervision, AEPIC consistently outperforms state-of-the-art semi-supervised clustering methods.

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while graph-based RAG is frequently hindered by search-time pruning, which may discard potentially valid reasoning paths. Existing hybrid approaches primarily adopt simple evidence concatenation or unidirectional enhancement, which fails to address the fundamental "Information Island" problem caused by asymmetric reasoning flows between unstructured text and structured graphs. We propose TGS-RAG, a unified framework for Text-Graph Synergistic enhancement. TGS-RAG introduces a bidirectional mechanism: (i) a Graph-to-Text channel that employs a Global Voting strategy from visited graph nodes to re-rank and refine textual evidence, filtering out semantic noise; and (ii) a Text-to-Graph channel that utilizes the Memory-based Orphan Entity Bridging algorithm. This algorithm utilizes textual cues to proactively resurrect valid but previously pruned reasoning paths from the search history without additional database overhead. Experimental results on multiple multi-hop reasoning benchmarks demonstrate that TGS-RAG significantly outperforms state-of-the-art baselines, achieving a superior balance between retrieval precision and computational efficiency.

Understanding overthinking in large reasoning models (LRMs) is crucial for interpretability as well as reasoning efficiency and effectiveness. However, existing approaches primarily adopt coarse-grained reasoning strategies, such as truncating Chains-of-Thought or switching reasoning modes, which reduce verbosity but are insufficient to actively guide reasoning toward more effective trajectories. To address these issues, we propose a training-free, interpretable framework that selects thinking words via attention heads to guide LRMs toward more effective reasoning. Specifically, we categorize thinking steps into effective and redundant states, identify the attention head that best discriminates between them as the Thinking Partition Head to construct an Effective Thinking Representation Space, and compute the Information Gain Ratio (IGR) between candidate thinking words and this space to select the word that steers reasoning toward a more effective direction. Extensive experiments on mathematical and scientific reasoning benchmarks, including AIME24, AMC23, MATH-500, GSM8K, and GPQA-D, show that our method consistently outperforms the strong baseline DEER, achieving average improvements of 1.2–1.3% in accuracy and 2.5–4.5% in compression rate. Compared to vanilla baselines, our approach yields larger gains of 2.6–6.3% in accuracy while reducing token usage by 22–43%.

Persuasive dialogue aims to alter people's attitudes or behaviors through conversation. While LLMs can generate emotional responses, they tend to use a uniform approach across varied scenarios, limiting their persuasive effectiveness. Diverse demands need varied persuasion strategies, which challenge both LLMs and human efforts. To address this, this paper incorporates the idea of meta-learning and proposes PersuHMM, an iterative learning approach for constructing the Hierarchical Meta-strategy Memory to generate Persuasive dialogue. Through the interaction between Meta‑layer and Task‑layer, the approach continuously accumulates automated meta‑strategies from generated outcomes and data labels, forming a persuasive meta‑strategy memory that balances efficiency and generalizability. To facilitate model retrieval and use, the meta-strategy memory is hierarchically organized via clustering for a clearer and more logical storage structure. Experimental results show that the hierarchical meta-strategy memory enhances both the persuasiveness and generalizability of the persuasion model, and even enables cross-model performance improvement.

This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal token usage. While existing LRMs rely on long-chain reasoning and excel at complex tasks, their system 1 thinking ability remains largely underexplored. This capability is essential as it reflects models' difficulty awareness and reasoning efficiency, both critical for real-world applications. We propose S1-Bench, a multi-domain, multilingual benchmark comprising model-simple system 1 questions. Our investigation of 28 LRMs reveals under-accuracy and inefficiency on system 1 problems. We find existing efficient reasoning methods either generalize poorly to simple questions or sacrifice performance for efficiency. Further exploration uncovers LRMs' early difficulty awareness accompanied by lower confidence, and shows that problem difficulty is implicitly encoded in hidden states. Code and the extended version of the paper with appendices are available at https://github.com/WYRipple/S1_Bench.

Abstractive summarization plays a crucial role in enabling efficient understanding of scientific literature, yet it inherently demands both linguistic fluency and factual faithfulness. Existing approaches often fail to reconcile these two requirements. Extractive methods rely on rigid sentence splicing that disrupts macro-level logical coherence, while large language model (LLM)-based generative approaches, despite mastering linguistic fluency, exhibit limited factual consistency. In this work, we propose ScholarSum, a hierarchical reflective graph-based framework that emulates a student–teacher writing process for fluent and faithful scientific summarization. ScholarSum first organizes the document into a hierarchical knowledge graph by segmenting it into semantically coherent units, whose multi-layered community structure captures global logic and macro-level themes. Guided by this global structure, the student generates an initial draft, which is subsequently refined through fine-grained evidence retrieval. To ensure factual consistency, a teacher-like reviewer then iteratively examines the draft, identifies unsupported content, and prompts targeted re-retrieval and rewriting until the summary meets rigorous quality standards. Extensive experiments demonstrate that ScholarSum significantly outperforms previous baselines in terms of both completeness and faithfulness. Our code is available at https://github.com/Xiaoyu-Tao/ScholarSum.

Event Causality Identification (ECI) is a crucial task in knowledge discovery that extracts structured causal relationships between annotated event mentions from unstructured text. However, existing approaches typically rely on extensive labeled data, which is scarce for specialized domains and topics. Although Large Language Models (LLMs) show strong promise for few-shot and zero-shot information extraction, they are prone to “causal hallucination,” generating unreliable and spurious causal links. To address these limitations, we propose LLM-SD (Large Language Model Self-Debate), a novel framework that formulates ECI as a structured debate among multiple identical instances of a single LLM. Causality is determined through the integration of adversarial evidence. The framework employs LLMs in distinct roles: an affirmative team argues for the existence of causality, a negative team argues against it, and an adjudication committee evaluates the evidence for determination. An evidence strength grading rule guides the quantification and integration of adversarial evidence. The automatic and LLM-driven verification finally produce a reasoned verdict for event causality. LLM-SD reduces spurious causal links resulting from causal hallucination in LLMs and identifies more long-distance causalities by promoting a balanced evaluation of arguments. Extensive experiments on three benchmark datasets demonstrate that LLM-SD achieves state-of-the-art performance in a zero-shot setting.

Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense. LLM routing aims to mitigate expenses while maintaining performance by sending queries to the most suitable model. However, existing methods cannot perform well for different user cost-performance preferences. To address this gap, we introduce a novel perceptive LLM routing paradigm for personalized and user-centric cost-performance optimization, which efficiently learns users' implicit preferences through little interaction. To handle the challenge of heterogeneous user needs, we formulate preference profiles as a set of distinct tasks in contextual bandit and propose MetaRouter, a meta-learning framework designed for preference-aware LLM routing. Experimental results show that MetaRouter outperforms strong baselines on both in-distribution and out-of-distribution tasks. Furthermore, it exhibits high efficiency in learning user preferences, robustness to changes in the routable LLMs, and scalability to multi-model routing.

Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and online teaching practices. Recent work has explored large language models (LLMs) for this task, achieving promising performance. However, LLMs still struggle to select the correct concept from a large-scale candidate set due to the high dimensionality of the decision space. In this paper, we propose a novel three-stage Select-Reason-Judge (SRJudge) framework, which empowers LLMs with selective reasoning capability for fine-grained knowledge concept tagging. Specifically, the Selector in Stage 1 first narrows the candidate concepts to a top-K shortlist by fine-tuning a small language model (SLM), e.g., BERT, since the top-K predictions hit the correct concept in most cases, thereby reducing the decision space of correct candidates. Next, the Stage 2 Reasoner employs a lightweight LLM for refined reasoning over the shortlisted candidates. It further integrates an improved reinforcement learning strategy with a dynamic task-specific reward function and a pruning mechanism to better align with human reasoning preferences. Finally, a larger LLM acts as a judger that evaluates the overall rationality of the reasoning process and its explanations to determine the final output. In addition, we construct two high-quality datasets for further validation, i.e., the biology dataset S_Bio and the physics dataset S_Phy. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines across benchmark datasets, verifying its effectiveness and superiority. Resources are available at: https://github.com/Nicozwy/SRJudge.