Tema

LLMs

3009documentos

250últimos 7 días

From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios

Recent multimodal large language models have advanced video understanding, but existing benchmarks mainly evaluate whether models can interpret observed visual content. In real-world scenarios, assistants must additionally anticipate what assistance is needed and decide when to provide it. To address this gap, we introduce P^3IBench, a benchmark for proactive video understanding in real-life streaming scenarios. It evaluates three complementary capabilities: daily perception, risk prediction and intervention. We benchmark 12 representative open-source and proprietary video-language models, including streaming and adapted non-streaming systems. Our evaluation shows that current models struggle to make well-calibrated response decisions. Finally, we construct additional proactive training data and train P^3I-Assistant-4B, achieving improvements on several tasks, though gains remain uneven across capabilities. Together, these findings show that effective proactive assistance requires not only visual understanding, but also precise response timing and appropriate restraint.

arXiv AI Papershace 29 días

BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition

On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models to reverse engineering and intellectual property theft. Trusted Execution Environments (TEEs) provide hardware-enforced isolation for on-device inference, yet most TEE-based parameter obfuscation relies on unilateral matrix transformations that obfuscate only output side. We identify a vulnerability in this design, termed the Solution Determinacy Property (SDP): the obfuscation secret is uniquely determined, exposing the structure of the true key and enabling attackers to break the protection. Under our attacks, representative methods GroupCover and ArrowCloak are reduced to negligible protection, with attack accuracy reaching over 2.4the full-shielding black-box baseline and recovering near-complete model functionality.To address this vulnerability, we propose BiShield-TEE, a bilateral framework that induces Ambiguous Solutions through joint obfuscation of input and output dimensions, hiding the true key among many equally valid candidates. Experiments across diverse models and datasets show that BiShield-TEE confines attack accuracy to the full-shielding black-box baseline, while achieving higher inference efficiency than prior methods on real hardware.Our code is available at https://github.com/laduiw/BiShield-TEE.

arXiv AI Papershace 29 días

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents

Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has received extensive attention, a different failure mode has been overlooked: procedural hallucination, in which an agent produces individually fluent and factually plausible utterances while deviating from the intended conversational process. We introduce DialFork, the first benchmark to measure this failure mode on raw dialogue text. DialFork is built by forking conformant dialogues at controlled turn positions and injecting one of four hallucination types, yielding 36,278 dialogues across 24 tasks in 12 domains; 30 human annotators validate the construction. We define three evaluation tasks that characterize procedural deviation at three granularities: how far a set of dialogues deviates from conformant ones (monitoring deployed agents), how far a single dialogue does (procedural retrieval), and at which turn a dialogue first goes off-track (real-time guardrails). For the first two, we propose dialog-flow-aware metrics, FlowKL and FlowScore, that compare dialogues by how they unfold rather than their content. At the dialogue level, FlowScore significantly outperforms all baselines across seven encoders, showing that semantic similarity is no substitute for procedural similarity. We release DialFork under the MIT license at https://github.com/idiap/dialfork, hoping the community will measure conversational process alongside content.

arXiv AI Papershace 29 días

When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark

Muon's gains in data efficiency motivate evaluating its performance under explicit data, time, and tuning budgets. On a single A100 GPU, we compare a reference single-device Muon implementation with AdamW across 17.7M- and 33.6M-parameter causal language models and 2.70M-parameter vision transformers. A common 23-candidate development budget selects configurations evaluated with five matched seeds, full validation trajectories, optimizer-step timing, and a frozen one-shot test. Muon reduces validation-loss area under the curve by 3.25--22.44\% at equal data and lowers test loss in all 20 primary pairs. In this configuration, Muon improves time-normalized loss area} by 19.68--22.31\% on vision, while AdamW is better by 3.38--6.96\% on language. The full Muon optimizer call, including auxiliary AdamW updates, consumes 56.1--69.6\% of training time, compared with 6.1--9.1\% for the AdamW baseline. Muon also has higher expected regret under restricted access to these candidate pools. These results characterize small models with reference kernels; their wall-clock ordering does not establish a ranking for larger models or optimized implementations.

arXiv AI Papershace 29 días

Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models

Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning in large language models (LLMs) remains vulnerable to catastrophic forgetting. A promising direction is to identify functionally specialized subnetworks within LLMs that enable targeted and resource-efficient adaptation. Using gradient-attribution profiling, we localize cognition-associated functional subnetworks exhibiting extremely low mutual overlap. Building on this finding, we propose Function-isolated Memory-Efficient Optimization (CiMEO), a continual learning framework that routes each training example to its corresponding functional subnetwork, restricting parameter updates and optimizer states to selected regions. Across 1.4 million sequential instructions, CiMEO achieves the highest average performance among the compared methods on five generative benchmarks spanning programming, examination-style tasks, and mathematical reasoning, while mitigating catastrophic forgetting. Subspace-overlap and principal-angle analyses further indicate that localized updates help preserve pre-trained representations, highlighting functional subnetwork localization as a practical approach to efficient and stable continual learning in LLMs.

arXiv AI Papershace 29 días

CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games

Large Language Models (LLMs) have shown impressive capabilities across many tasks, including processing large amounts of text, following instructions, and generating ideas. This allows the use of such models in various contexts, including games and Tabletop Role-Playing Games (TTRPGs), such as Dungeons & Dragons. However, these games include many complex components, from crafting interesting stories to adhering to rules, while allowing some freedom in players' actions. In this work, we first highlight key components that LLMs should exhibit in the context of TTRPGs. Then, we introduce our framework, CriticaLLM, a fully automated Game Master that can run entire TTRPG games, from creating diverse and interesting stories to managing exploration and combat phases. We evaluate our framework with actual TTRPG players and examine the diversity of generated plots and antagonists across four LLMs of varying sizes. Overall, our framework appears to be a promising option for running entire TTRPG games.

arXiv AI Papershace 29 días

SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics

Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varies in natural settings. To enable the study of real-world linguistic meaning in the brain, we introduce SCRIBE, a framework grounded in a neuroscience-informed semantic space that leverages an ensemble of open-source large language models to generate interpretable, word-level semantic representations of arbitrary text. In a behavioral study with 921 participants, we show that human semantic feature judgments vary systematically with context, and that SCRIBE captures these shifts, reaching 75-81% of the estimated human noise ceiling. Using brain activity recorded while participants listen to naturalistic stories, we further demonstrate that SCRIBE predicts neural responses in language-selective brain regions, significantly outperforming non-contextual semantic representations. Variance partitioning reveals that SCRIBE explains unique brain-predictive information beyond syntactic features, suggesting that its representations capture aspects of linguistic meaning not accounted for by the measured syntactic features. Together, these findings establish SCRIBE as a scalable and interpretable foundation for studying natural language semantics in the brain.

arXiv AI Papershace 29 días

Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair

When code-repair agents fail, final tests reveal that a patch is wrong but not which earlier commitment caused it or which software obligation failed. Poison Valleys traces this path in 1,844 model requests on two synthetic Python cases: PersistQueue adds atomic batch claiming to a disk-backed queue, while Dijkstra adds source-sensitive filtering to shortest-path search. We define plausible but incorrect software mechanisms, place each in a model's hypothesis, implementation plan, or both, and evaluate the generated code with an Oracle and targeted diagnostic coordinates. Moving the misconception from hypothesis to plan increased failure by 32.2% in PersistQueue and 28.9% in Dijkstra after matching the experimental mix. Different misconceptions produced distinct, model-dependent patterns of violated obligations, although several could converge on the same behavior. This creates a measured connection from upstream misconception to code mechanism and failure form. Code, data, and demo: https://poisonvalleys.org.

arXiv AI Papershace 29 días

Decomposing Brain-LLM Alignment with Interpretable Semantic Representations

Large language models (LLMs) predict neural responses during naturalistic language comprehension, but the linguistic information underlying this brain alignment remains difficult to interpret. We use SCRIBE, an interpretable contextual semantic representation spanning 65 neurocognitively grounded semantic properties, as a lens for decomposing the brain alignment of one LLM, LLaMA2-7B. Using variance partitioning between LLaMA2-7B and SCRIBE on naturalistic fMRI data from seven participants listening to narrative stories (Moth Radio Hour), we separate brain-predictive variance shared between the two representations from variance unique to each. We find that shared variance is the dominant component across the whole brain and language-related regions, while both representations also retain significant unique contributions. We then examine whether the concreteness of individual semantic properties relates to shared and SCRIBE-unique brain-predictive variance. Concrete properties show greater shared variance with LLaMA2-7B than abstract properties across the whole brain and most examined regions, whereas abstract properties do not show greater SCRIBE-unique variance. Finally, property ablations reveal that semantic contributions extend across multiple dimensions, with cumulative effects on both shared and SCRIBE-unique variance. Together, these results show that, for LLaMA2-7B on this dataset, a substantial portion of brain-LLM alignment is associated with interpretable semantic information, while revealing complementary brain-predictive semantic information beyond the LLaMA2-7B representation.

arXiv AI Papershace 29 días

ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing

Internal solitary wave (ISW) remote sensing requires task parameters and spatial information to be transferred across image acquisition, detection, stripe extraction, and propagation prediction. Here, we present ISW-Agent, which integrates large language model (LLM) interpretation with n8n workflows and independent scientific models through structured task constraints, geospatial transformations, and stage-specific output validation. In tests of 120 Chinese instructions per backend, GPT-5.6 Sol and DeepSeek both achieved a strict task-match rate of 94.2%, with all intents and execution decisions matching the reference. Sentinel-1 cases demonstrated continuous processing from dialogue requests to wavefront prediction for the specified scene. Of 50 timed scenes, 39 completed detection, extraction, and prediction with a median turnaround time of 48.04 s; 11 stopped after empty extraction. Across 3,408 controlled fault-injection runs, retries recovered 234 transient-failure conditions and output validation rejected 234 structural defects, while 61 provenance or completeness errors indicated the need for content-consistency checks. Overall, ISW-Agent thus connects natural-language requests to traceable spatial processing chains for multimodel ISW analysis.

arXiv AI Papershace 29 días

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier shared by every engine. We study such a tier in a disaggregated deployment of GLM-5.3, an FP8 mixture-of-experts model with multi-head latent attention (MLA), on 8xB300 nodes running prefill context parallelism (PCP8). Enabling the remote tier (LMCache with a Valkey store) left median time-to-first-token unchanged but raised the 16k-token p99 from 3.96 s to 17.3 s. Replaying a production request stream on an isolated engine, we find that a remote hit took 0.88 s against 0.31 s to recompute the prompt, and that synchronous loading turned a hit-heavy stream into an unstable queue: p99 83.32 s with the GPUs 7% busy. A two-term cost model explains both: a hit pays off only if the tier delivers more than B* = sR (2.53 GB/s for this model and GPU), and a fixed per-hit engine cost (T0 ~ 0.33 s) means that hits on prompts shorter than about 17k tokens cannot beat recompute at any bandwidth. Guided by the model, we (i) shard the MLA KV store across PCP ranks, with a proof that the existing minimum-over-ranks lookup returns the longest cached prefix and a load protocol that can never desynchronize collectives; (ii) partition the remote tier by rank, one server instance per rank with no coordination, which raises GET bandwidth 6.3x to 10.76 GB/s; (iii) add asynchronous loading to the sharded store; and (iv) fix three client bugs that caused unbounded stalls. On the hit-heavy stream, with 98.5% of prompt tokens served from the remote tier, p99 falls from 83.32 s to 0.67 s. The sharded store raises prefill throughput by 14%, and by 34% together with an upstream kernel fix. All changes are submitted upstream to LMCache.

arXiv AI Papershace 29 días

MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling

Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing methods either optimize external experience scaffolds or train experience-related behavior on specific task distributions, leaving open whether experience learning itself can become a transferable model capability. Training such a capability calls for supervision beyond isolated tasks, which mainly support in-episode problem solving rather than revealing what knowledge remains useful across episodes. In this work, we introduce MetaExp, a scalable framework that trains this capability through verifiable task families with controlled cross-task structure. Each family preserves a reusable factor while varying task-specific realizations, enabling transfer without direct solution reuse. We propose two complementary designs: Shared-Tool families keep black-box tools fixed across tasks to elicit operational experience, while Shared-Workflow families preserve latent procedures across changing realizations to elicit procedural experience. We scale environments under both designs, collect and filter sequential interaction trajectories, and fine-tune Qwen3.5-122B-A10B on 4,956 trajectories from 1,000 task families. With parameters frozen during downstream evolution, MetaExp improves by +8.5 points on SpreadsheetBench, peaks at +2.3 on APEX-Agents, and improves by +14.8 on AutomationBench. The gains persist under domain-excluded training, supporting experience learning as a transferable capability for continued non-parametric improvement after deployment.

arXiv AI Papershace 29 días

FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors

Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by reading the context and another model's response, even from a proprietary generator. Attention-based detectors use summary statistics of the proxy's attention weights, but standard pipelines materialize the attention matrix, whose memory grows quadratically with sequence length. We compute these statistics without materializing attention, by accumulation in the FlashAttention pass, sparse lookups after it, or a second tiled pass over the scores, and classify them by this path into nearly free and costlier ones. On an H100, the statistics of five published detectors add 16% to the latency of a Qwen3-8B forward at 2K tokens, falling to 1.4% at 35K, and store 22.5 KiB per response token. On three benchmarks, probes trained on frozen Qwen3 proxies of 0.6B to 8B parameters prove strong detectors: a 4B proxy outperforms the strongest of nine zero-shot 4-9B LLM judges in F1 on two of the three, the proxies match or outperform specialized grounding checkers of up to 7B parameters, probing each proxy beats prompting it as a judge, and adding attention features significantly improves F1 in half of the 12 benchmark-proxy pairs, never significantly lowering it.

arXiv AI Papershace 29 días

Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes

Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to free-form patient notes requires precise variable extraction combined with the exact execution of complex formulas, scoring rules, and output conventions. Relying solely on direct large language model (LLM) prompting is unreliable in this context, as rule recall, parameter extraction, arithmetic reasoning, and formatting become entangled within a single generative step. To address these limitations, we propose a tool-augmented LLM framework for reliable medical calculation from patient notes. The framework retrieves and structures calculator specifications, generates reusable executable tools, and uses a constrained extractor to map each patient note to calculator-ready inputs. The tools then perform deterministic calculation, separating clinical language understanding from rule execution and arithmetic. Evaluated on the MedCalc-Bench dataset, our method achieves 86.73% final-answer accuracy, outperforming the one-shot prompting and supervised fine tuning-only baselines by 24.0 and 17.27 percentage points. Ablation and error analyses show that these performance gains are primarily driven by rule-grounded tool synthesis and schema-constrained extraction, whereas remaining failures are concentrated in clinical-semantic extraction and benchmark-specific output contracts. By grounding calculator logic in executable tools, the proposed approach alleviates arithmetic hallucinations and improves the computational reliability of the final clinical outputs.

arXiv AI Papershace 29 días

Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation

Every story has two orders: the order in which its events happen and the order in which they are told. A story is nonlinear when the two differ. We introduce a benchmark of 83 published works that measures whether language models can tell nonlinear stories. For each work, we annotate one list of events in both orders, together with a story graph of causal dependencies, character knowledge, and the questions the telling raises and resolves. Given events in chronological order, all 19 models tell them, on average, more chronologically than the published works do; asked for a specific structure, they land within the human range about half the time. We then compare a model's stories of the same events under different conditions, using both an automated judge and 71 human readers. Both prefer the chronological story a model writes by default to the nonlinear one it writes on request, which readers find harder to follow in 81% of decisive judgments. Readers also prefer stories written from the story graph to stories constrained to the published telling order (72% of decisive judgments), a difference the judge does not detect. Our results suggest that following an instruction to reorder a story is not yet the same as telling it well out of order.

arXiv AI Papershace 29 días

Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON

Ontologies are widely used to represent and organize complex knowledge in domains such as biomedicine and healthcare. However, constructing reliable ontologies remains challenging, as class hierarchies, whether manually or automatically constructed, may contain subtle subsumption errors that require careful refinement. We study this problem in CASTON, a casting-domain ontology, and present a lightweight but scalable refinement workflow that combines a fine-tuned ontology embedding model with Large Language Models (LLMs). The embedding model is used to extract a limited number of candidate axioms for refinement together with possible replacement candidates, and an LLM then returns repair suggestions. In a small expert evaluation, the default configuration using a CASTON-fine-tuned OnT embedding model and Qwen3-8B produced reliable high-confidence repairs: all six high-confidence replacements were accepted by both domain experts. The implementation is available at https://github.com/HuiYang1997/OntRefine.

arXiv AI Papershace 29 días

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a much smaller model. Existing ways of sharing this work keep the strong model as the generator: routers and collaborative agents decide which model handles each query or step, and speculative methods check a small model's drafts one step at a time, usually against the strong model's own action. We introduce SpecAgent, a collaboration protocol that turns the strong model from the author of each step into a reviewer of steps drafted by a weak model. The weak model executes read-only tool calls as it drafts, so that every step is grounded in real observations, and holds the first action that would modify the environment. The strong model then verifies the drafted segment in a single prefill pass, commits the longest prefix it judges semantically valid, and repairs the first rejected step. Because verification replaces autoregressive decoding with parallel prefill, the strong model decodes only short verdicts and occasional repairs rather than every step. On τ^2-Bench, SpecAgent comes within one point of the strong model's success rate while roughly halving memory traffic and wall time, and on AutomationBench and VitaBench it recovers 44-75% of the quality gap while lowering both. In an edge-cloud deployment on MCP-Atlas with three cloud models, it closes 53-75% of the weak-strong quality gap while the strong model generates at most half as many tokens. These results suggest that a strong model need not author every step of an agent: reviewing grounded drafts retains most of its quality while cutting both latency and memory traffic.

NVIDIA AI Bloghace 29 días

The Nordics and NVIDIA Show What’s Possible When a Region Commits to Advanced Computing

The Nordic countries have become the European leader in unicorn startup density, producing the most emerging companies valued at $1 billion or more per capita on the continent. Now, a new chapter for the region is unfolding as countries race to build one of Europe’s most consequential technology ecosystems. The many computing advancements already underway […]

Apple Machine Learning Researchhace 29 días

Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate nearest-neighbor search. We study an alternative Plan-then-Retrieve (PtR) paradigm in which the LLM first generates Abstract Tool…

Apple Machine Learning Researchhace 29 días

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

MLX on Mac with Apple silicon lets AI researchers and developers experiment locally with the latest models and methods in a private environment. The open-source array framework leverages the unified memory architecture of Apple silicon, enabling anyone to run new inference and fine-tuning methods on their own hardware and explore other AI techniques. In a previous post , we highlighted…