In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on pruning offers a practical solution, yet existing methods rely on sequential token removal which is computationally intensive. We present DiffuMask, a diffusion-based framework integrating hierarchical shot-level and token-level pruning signals, that enables rapid and parallel prompt pruning via iterative mask prediction. DiffuMask substantially accelerates the compression process via masking multiple tokens in each denoising step. It offers tunable control over retained content, preserving essential reasoning context and achieving up to 80% prompt length reduction. Meanwhile, it maintains or improves accuracy across in-domain, out-of-domain, and cross-model settings. Our results show that DiffuMask provides a generalizable and controllable framework for prompt compression, facilitating faster and more reliable in-context reasoning in LLMs.

Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query–table relevance and ignore table–table compatibility. We introduce REaR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REaR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REaR is retriever-agnostic and consistently improves dense/ sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g., ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REaR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).

Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDDL annotations and may exploit solver success in semantically unfaithful ways. We study how to learn faithful natural-language-to-PDDL formalization using only solver feedback, without human-written demonstrations. We propose a solvergrounded multi-role reinforcement learning framework where a single language model acts as an Actor, Judge, and Editor for generation, verification, and repair. The Actor proposes PDDL specifications, the Judge provides a solver-calibrated quality signal, and the Editor performs bounded diagnostic-conditioned refinement. On PlanBench, our method improves average success from 35.5

AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial. Most prior methods build the routing framework by training a single model across all strategies, which demands full retraining whenever new strategies appear and leads to high overhead. Attempts at such continual routing, however, often face difficulties with generalization. Prior models also typically use a single input representation, limiting their ability to capture the full complexity of the routing problem and leading to sub-optimal routing decisions. To address these gaps, we propose CONCUR, a continual routing framework that supports both constrained and unconstrained routing (i.e., routing with or without a budget). Our modular design trains a separate predictor model for each strategy, enabling seamless incorporation of new strategies with low additional training cost. Our predictors also leverage multiple representations of both tasks and computation strategies to better capture overall problem complexity. Experiments on both in-distribution and out-of-distribution, knowledge- and reasoning-intensive tasks show that our method outperforms the best single strategy and strong existing routing techniques with higher end-to-end accuracy and lower inference cost in both continual and non-continual settings, while also reducing training cost in the continual setting.

Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conventional benchmark evaluations typically assume static schemas and well-formed user inputs. In this work, we introduce a robustness evaluation benchmark containing approximately ten types of perturbations and conduct evaluations under both traditional and agentic settings. We assess multiple state-of-the-art large language models (LLMs), including Grok-4.1, Gemini-3-Pro, Claude-Opus-4.6, and GPT-5.2. Our results show that these models generally maintain strong performance under several perturbations; however, notable performance degradation is observed for surface-level noise (e.g., character-level corruption) and linguistic variation that preserves semantics while altering lexical or syntactic forms. Furthermore, we observe that surface-level noise causes larger performance drops in traditional pipelines, whereas linguistic variation presents greater challenges in agentic settings. These findings highlight the remaining challenges in achieving robust NL2SQL systems, particularly in handling linguistic variability.

Artificial intelligence (AI) and hardware (HW) are advancing at unprecedented rates, yet their trajectories have become inseparably intertwined. The global research community lacks a cohesive, long-term vision to strategically coordinate the development of AI and HW. This fragmentation constrains progress toward holistic, sustainable, and adaptive AI systems capable of learning, reasoning, and operating efficiently across cloud, edge, and physical environments. The future of AI depends not only on scaling intelligence, but on scaling efficiency, achieving exponential gains in intelligence per joule, rather than unbounded compute consumption. Addressing this grand challenge requires rethinking the entire computing stack. This vision paper lays out a 10-year roadmap for AI+HW co-design and co-development, spanning algorithms, architectures, systems, and sustainability. We articulate key insights that redefine scaling around energy efficiency, system-level integration, and cross-layer optimization. We identify key challenges and opportunities, candidly assess potential obstacles and pitfalls, and propose integrated solutions grounded in algorithmic innovation, hardware advances, and software abstraction. Looking ahead, we define what success means in 10 years: achieving a 1000x improvement in efficiency for AI training and inference; enabling energy-aware, self-optimizing systems that seamlessly span cloud, edge, and physical AI; democratizing access to advanced AI infrastructure; and embedding human-centric principles into the design of intelligent systems. Finally, we outline concrete action items for academia, industry, government, and the broader community, calling for coordinated national initiatives, shared infrastructure, workforce development, cross-agency collaboration, and sustained public-private partnerships to ensure that AI+HW co-design becomes a unifying long-term mission.

Epilepsy is a common neurologic disorder characterized by recurrent, unprovoked seizures, and detailed phenotypes are essential for treatment selection, prognostication, and outcomes research. Although electronic health records provide rich longitudinal data, structured fields such as diagnostic codes fail to capture these phenotypes, which remain buried in free-text clinical notes. We developed and evaluated two transformer-based language models for automated epilepsy and seizure type phenotyping at an academic epilepsy center: a fine-tuned masked language model (BERT) and a reasoning-optimized large language model (DeepSeek-R1), benchmarked against pairwise inter-rater agreement among board-certified epileptologists. For coarser tasks, both models matched expert agreement: classifying epilepsy type as focal, generalized, or other (Matthews correlation coefficient: DeepSeek = 0.85, BERT = 0.73, human = 0.77) and seizure type as convulsive or non-convulsive (DeepSeek = 0.74, BERT = 0.60, human = 0.49). For more granular tasks, DeepSeek maintained expert-level performance, whereas BERT declined. Deploying DeepSeek-R1 on 77,049 notes from 18,566 patients yielded patient-level phenotypes consistent with expected clinical patterns, including diagnostic stabilization, seizure type co-occurrence, and outcome differences by epilepsy type. Transformer-based models can extract expert-level epilepsy phenotypes at health-system scale, demonstrating the feasibility of automated phenotyping for large-scale epilepsy research and, with prospective validation, for future clinical decision support.

Reference-free image-to-text evaluators are now standard for scoring image-caption alignment, yet it is unclear whether they respect semantic invariances. We present an invariance probe on five popular evaluators (CLIPScore, PAC-S, UMIC, FLEUR, and a deterministic LLM judge) under semantics-preserving perturbations along three axes – spatial (flips, context-preserving repositioning, light rotations), object (scale, category), and socio-linguistic framing (cultural/economic adjectives with neutral and length-matched controls). Across curated slices of three detection datasets and three caption evaluation suites, we find consistent non-semantic sensitivities, where benign spatial edits and simple phrasing changes shift scores by ≈6–9% on average, and for systems separated by just 0.7%, these shifts can cause ranking flips in up to ∼37% of cases, particularly under spatial changes. A small human study also supports this finding and confirms that annotators generally judge perturbed pairs as equally correct, so these shifts reflect metric behavior rather than semantic change. We further propose invariance-calibrated scoring, a post-hoc adjustment that roughly halves median absolute sensitivity while retaining correlation with learned caption evaluators.

Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations. Existing methods often struggle with retrieving the right tables and columns, generating accurate JOINs and UNIONs, and generalizing across diverse schemas. To address these issues, we introduce UNJOIN, a two-stage framework that decouples the retrieval of schema elements from SQL logic generation. In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name. This allows the model to focus purely on accurate retrieval without being distracted by the need to write complex SQL logic. In the second stage, the SQL query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic. Evaluations on SPIDER and BIRD datasets show that UNJOIN matches or exceeds the state-of-the-art baselines. UNJOIN uses only schema information, which does not require data access or fine-tuning, making it scalable and adaptable across databases.

For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism. We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer. On a 40-task verifiable algorithmic benchmark, deterministic code execution outperforms natural-language reasoning by +31.6pp. We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp). These results suggest that, in our evaluated setting, changing the intermediate representation alone does not explain the tool-use advantage, providing evidence for the performance gains requiring reliable external execution. We formalize this intuition with a simple statistical decision-theoretic model that characterizes when execution dominates end-to-end risk in our disentangled trace-generation/execution regime. We validate our theory using a reconstruction intervention that leverages a proxy language model to infer natural-language reasoning traces from code representations, recovering performance comparable to the original natural-language reasoning pipeline. All experiments are at https://github.com/TerryTong-Git/ToolProj.

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches introduce randomness without adequate robustness. Self-consistency improves reliability by aggregating multiple rollouts, but incurs significant computational overhead. We propose an entropy-guided decoding framework that introduces token-level adaptivity into generation. At each step, the model computes the entropy of the token distribution, identifies high-uncertainty positions, and selectively branches on these vulnerable points. A dynamic pool of partial rollouts is maintained and expanded until solutions are completed, concentrating computation where uncertainty is greatest and avoiding unnecessary exploration in confident regions. To enable efficient termination, we apply a rollout-level Entropy After (EAT) stopping criterion by performing entropy evaluation after the full reasoning trace, rather than incrementally at every step. Experiments on GSM8K, AMC2023, and their perturbed variants demonstrate that our method achieves consistently strong accuracy. Notably, on smaller LLMs, performance is comparable to GPT-5 while operating at a fraction of the cost.

Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their preferences, intents, habits, social relationships, and needs unfold over time. Today's systems can personalize within individual apps or tasks, but personal intelligence as a whole remains under-measured: how agents build cross-context user understanding, support steerable recommendation systems, act proactively across platforms, and avoid over-personalization. We introduce PersonaMem-v3, a real-world-grounded benchmark and evaluation harness for omni-platform personal intelligence. PersonaMem-v3 is seeded from more than one million anonymized real-world engagement histories, most of which are implicit signals, and uses them to construct time-indexed user digital worlds across social media, chatbot, calendar, and AI-companion with preference evolvement over time. The benchmark brings personalization, LLM-powered recommendation, proactiveness, agentic tool use, and geo-temporal reasoning into one framework, anchored in psychology, social-linguistics, and user-behavior theories. It evaluates whether AI agents can infer holistic user understanding from cross-platform evidence, personalize responses, rerank recommendations on social media, follow user steering through natural language, and hold back when personalization would be inappropriate, repetitive, outdated, or unnecessary. PersonaMem-v3 points toward LLM-powered personal intelligent agents that work with existing scalable recommendation infrastructure while making personalization more interactive, agentic, and aligned with how real users experience their digital lives.

Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness variants apply surface-level perturbations (paraphrases, renamings, number swaps, distractors) that largely preserve the underlying facts, and static releases can themselves become memorization targets over time. We introduce GSM-SEM, a reusable and stochastic framework for generating semantically diverse benchmark variants with substantially higher semantic variance than prior approaches. GSM-SEM perturbs problem statements by modifying entities, attributes, and/or relationships, frequently altering underlying facts and requiring models to recompute solutions under new conditions, while constraining generation to preserve the original calculations/answer and approximate problem difficulty. GSM-SEM generates fresh variants on each run without requiring re-annotation, reducing reliance on static public benchmarks for evaluation and thereby lowering the bias of memorization. We apply GSM-SEM on GSM8K and two existing variation suites (GSM-Symbolic and GSM-Plus), producing GSM8K-SEM, GSM-Symbolic-SEM, and GSM-Plus-SEM. Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28

Benchmarking the capabilities of AI systems, including Large Language Models (LLMs) and Vision Models, typically ignores the impact of uncertainty in the underlying ground truth answers from experts. This ambiguity is not just limited to human preferences, but is also consequential even in safety critical domains such as medicine where uncertainty is pervasive. In this paper, we introduce a probabilistic paradigm to theoretically explain how high certainty in ground truth answers is almost always necessary for even an expert to achieve high scores, whereas in datasets with high variation in ground truth answers there may be little difference between a random labeller and an expert. This characteristic also manifests when comparing models, where uncertainty obfuscates differences between poor and high performing models. Therefore, ignoring uncertainty in ground truth evaluation data can result in the misleading conclusion that a non-expert has similar performance to that of an expert. Using the probabilistic paradigm, we thus bring forth the concepts of expected accuracy and expected F1 to estimate the score an expert human or system can achieve given ground truth answer variability. Our work leads to the recommendation that when establishing the capability of a system, results should be stratified by probability of the ground truth answer, typically measured by the agreement rate of ground truth experts. Stratification becomes critical when the overall performance drops below a threshold of 80

Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with long, noisy, and weakly labeled audio due to their reliance on contrastive learning and large-batch training. We propose a novel multimodal retrieval framework that refines audio and text embeddings using a cross-modal embedding refinement module combining transformer-based projection, linear mapping, and bidirectional attention. To further improve robustness, we introduce a hybrid loss function blending cosine similarity, ℒ_1, and contrastive objectives, enabling stable training even under small-batch constraints. Our approach efficiently handles long-form and noisy audio (SNR 5 to 15) via silence-aware chunking and attention-based pooling. Experiments on benchmark datasets demonstrate improvements over prior methods.

Conventional wisdom for selecting supervision data for multimodal large language models (MLLMs) is to prioritize datasets that appear similar to the target benchmark, such as text-intensive or vision-centric tasks. However, it remains unclear whether such intuitive similarity reliably predicts downstream performance gains. In this work, we take a first step toward answering a practical question: can we estimate the influence of a training dataset on a target benchmark before any training is performed? To investigate this question, we conduct an in-depth analysis of transfer across 14 vision-language datasets spanning 7 diverse tasks. Our results show that intuitive task similarity is an unreliable predictor of transferability, and that generalization depends more on the specific dataset than on its broad task category. Motivated by this finding, we propose DATAPROPHET, a simple and effective training-free metric that combines multimodal perplexity, similarity, and data diversity. Experiments show that DATAPROPHET produces supervision-data rankings that strongly correlate with rankings based on actual post-training performance gains, achieving a Kendall's tau of 86.0

Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instructions frequently lead to tool mis-selection and incorrect slot/value instantiation. We hypothesize that this is due to two root causes: generic, one-size-fits-all prompts that ignore tool-specific nuances, and underspecified tool schemas that lack clear guidance on when and how to use each tool and how to format its parameters. We introduce Joint Tool-Prompt Reflective Optimization (JTPRO), a framework for improving tool-calling reliability in trace-supervised settings by iteratively using rollout-driven reflection to co-optimize global instructions and per-tool schema/argument descriptions for accurate tool selection and argument instantiation in large tool inventories. JTPRO is designed to preserve only tool-local cues needed for correct disambiguation and slot filling. We evaluate JTPRO across multi-tool benchmarks, which account for different number of tools using three metrics: Tool Selection Accuracy (TSA), Slot Filling Accuracy(SFA), and Overall Success Rate(OSR) (correct tool + correct slots + correct values). JTPRO consistently outperforms strong baselines, including CoT-style agents, and reflective prompt optimizers such as GEPA by 5

Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be answered over large, heterogeneous table collections pooled from many sources, without clean scoping signals such as database identifiers. Here, dense retrieval (DR) achieves high recall but returns many distractors, while join-aware alternatives often rely on extra assumptions and/or incur high inference overhead. We propose CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache. At inference time, DR returns top-K candidates; a single LLM call selects a coherent, joinable subset, and a simple additive adjustment step restores strongly compatible tables. Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is stable while hallucinations are stochastic, cross-regime agreement provides a precise signal of internal uncertainty. We leverage this signal to implement a training-free abstention policy that requires no retrieval or fine-tuning. Our results show that disagreement-based abstention outperforms standard uncertainty baselines as an error detector, improving both F1 and AUROC across settings. This demonstrates that decomposition-based prompting can serve as a practical diagnostic probe for model reliability in closed-book QA.