每天知道
你的领域
出了什么

Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update. For every new domain, the user is left with two hard systems problems: standing up an isolated environment for each of hundreds of concurrent trajectories and connecting it to training, and scheduling the rollout so that the GPU stays busy across long, multi-turn episodes that spend much of their time stalled on slow tool calls. We present MCP-Universe RL (MCP-U RL), an open-source framework that takes over both. It uses the Model Context Protocol (MCP) as the interface to the environment, so any tool already exposed as an MCP server plugs into training with no RL-specific integration code. It builds the two missing layers once and reuses them across domains: an environment-orchestration layer that provisions, isolates, and recycles the MCP environments over a pluggable container backend, and a rollout-orchestration layer whose staged pipeline overlaps trajectories to keep the GPU busy while episodes wait on tools. A backend-agnostic training layer then applies the update through an existing RL backend, with veRL and slime integrations. With one configuration, changing only the task specification, we train software-engineering, deep-research, and general tool-use agents on gpt-oss-20b and improve task reward in all three.

Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work demonstrates that LLMs achieve superior accuracy in function calling in instruction-following contexts (i.e., standard user-assistant interactions) rather than a tool calling context. We introduce Instruction-Followed Function Calling (IFFC), a novel framework that decouples function-calling logic from the primary LLM and delegates it to a dedicated smaller model operating within the instruction-following paradigm. Our method consistently outperforms both native function calling (NFC) and prompt-based function calling (PFC) baselines, with particularly strong gains on reasoning-oriented LLMs. Furthermore, we demonstrate that IFFC maintains robust performance under aggressive quantization, enabling efficient on-device deployment without significant accuracy degradation. This work establishes a new paradigm for reliable, resource-efficient function calling in edge-computing scenarios.

Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions, but the presence of multiple agents does not inherently guarantee coherent reasoning or outputs that align with task objectives. This paper introduces a quantitative ethnographic (QE) approach for diagnosing and redesigning multi-agent LLM systems based on the discourse produced through agent interactions. We test this approach using automated essay scoring as an example context, applying Epistemic Network Analysis (ENA) to model a five-agent multi-agent debate system and examine differences between debates that produced correct versus incorrect scoring decisions. Results show that, in the initial system, correct scoring decisions were characterized by rubric-grounded justification, agreement, and elaboration. Incorrect scoring decisions, in contrast, were characterized by extended proposition-challenge-response exchanges that were less consistently tied to rubric criteria. We then used the findings to revise the agents' prompts. The revised system improved exact scoring accuracy from 27.78% to 40.28% and shifted the discourse of incorrect debates toward the rubric-grounded pattern of correct ones, making the two nearly indistinguishable. Based on these results, we argue that QE can support a diagnostic-to-redesign loop for AI reasoning by tracing how patterns of agent interaction relate to system performance, informing prompt redesign, and evaluating whether those redesigns change both outcomes and interaction patterns.

Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents. Prevailing agent self-evolution paradigms typically rely on a core assumption: equipping LLMs with skill memories derived from successful trajectories will monotonically improve their problem-solving capabilities. However, probe analyses reveal that extracting skills solely from successful trajectories traps the model in a Skill Imitation Trap. For tasks that resemble past successes but require different tools, retrieving more skills paradoxically increases the model's confidence in wrong tool calls---procedure skills raise the wrong-tool margin by $47%$ over a memory-free baseline. To overcome this limitation, we propose Boundary-Aware Skill Memory (BASM), which augments each skill with explicit boundary fields---applicability conditions, risk cues, avoidance rules, and recovery notes. These fields transform each retrieved skill from an unconditional action template into state-conditioned guidance: the agent applies the skill when its conditions hold, suppresses inapplicable tool calls when they do not, and issues targeted repairs when execution fails. Across three agent benchmarks and four model scales, BASM consistently outperforms success-distilled skill-memory baselines: it improves task success rate by up to $23.8%$ on AppWorld, accuracy by up to $5.0%$ on BFCL, and reduces attack success rate by $4.6%$ on AgentDojo, while simultaneously reducing average AppWorld steps by up to $6.6%$ relative to the memory-free baseline.

Delta-Rule recurrent models maintain a fixed-size state, enabling $O(1)$ inference memory but potentially becoming unstable under extreme-context extrapolation. By tracking RWKV-7 over sequences of up to 100M tokens, we empirically identify a distinct failure pattern: localized norm explosion atop a relatively sparse substrate, rather than global state saturation. Analysis of the recurrent update suggests that persistent decay keeps weakly updated entries small, whereas uneven injections allow a few channels to accumulate extreme values. Motivated by this diagnosis, we propose State Anomaly Neutralization (SANE), which applies adaptive $\tanh$ compression at chunk boundaries while preserving the intra-chunk parallel structure. Within a safe threshold range ($3 \le α\le 5$), SANE matches the baseline on 11 short-context reasoning benchmarks with no statistically significant degradation. After a 100M-token prefix, which exceeds the training length by over $24{,}000\times$, SANE retains functional reasoning ($33.46$--$35.56$) while the baseline encounters numerical overflow. In contrast, overly permissive thresholds ($α\ge 8$) remain numerically stable but lose reasoning capability entirely, showing that numerical stabilization alone does not guarantee functional reasoning and revealing a capacity--stability trade-off in state compression.

While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the Softmax-attention ViT backbone of a trained detector into a linear-attention one is not a trivial drop-in replacement. Directly swapping the attention operator leads to severe performance degradation, and generic label-free distillation, though effective for classification, often fails on detection tasks. We argue that the central challenge is detector-interface preservation: the converted backbone must reproduce the exact feature tensors expected by the fixed downstream detector, rather than merely imitating internal Softmax hidden states. To address this, we introduce Detector-Interface Distillation (DiD), a label-free conversion method that exclusively trains the linear-attention backbone by aligning detector-facing interface tensors with those of a frozen Softmax teacher. On DOTA-v1.5, DiD substantially outperforms established baselines and matches supervised, fully trained linear models. Adaptation completes in roughly 87 minutes on 4 GPUs, and the linearized backbone cuts inference latency by ~62% and peak memory by ~49%. We hope our findings offer the community a simple, label-free route to reusing trained Softmax detectors as efficient linear ones, and encourage interface-aware objectives in future architecture-conversion work.

Low-precision optimizer-state methods are commonly designed and evaluated for dense Adam-style first and second moments. Memory-efficient optimizers depart from this setting: Adafactor factorizes second moments, CAME adds factored confidence states, and APOLLO maintains statistics in a projected gradient space. Consequently, an equal amount of state reconstruction error can induce different update errors depending on state topology and update semantics. We first characterize this heterogeneity in optimizer-state traces from language model pre-training. We then introduce Adaptive Log-Space (AL) quantization, a block-wise representation for non-negative states that adapts its nonzero range per block and enforces the exact-zero invariant $q = 0 \Leftrightarrow x = 0$. AL8 and AL16 are combined with independent signed-momentum encodings and state-specific precision choices rather than a single policy for every state. Across 96 runs totaling 214.7 GPU-hours, we evaluate dense, factored, confidence, and projected states in AdamW, Adafactor, CAME, and APOLLO paths. On a 20K-step TinyLlama-1.1B pre-training benchmark, an AdamW configuration with AL8 second moments and uniform 8-bit momentum reaches 72.90 perplexity, compared with 72.48 for FP32 AdamW and 73.54 for an 8-bit dynamic-quantization baseline, while reducing measured optimizer-state storage from 8392.7 to 2119.2 MiB. CAME exposes a different precision regime: promoting its non-negative states to AL16 recovers 86.16 perplexity versus 86.68 for the full-precision reference, whereas all-AL8 reaches 90.19. A 100K-step GPT-2 experiment further shows that topology-aware parameter protection reduces the late-loss gap of quantized Adafactor from +0.1185 to +0.0159 in the evaluated setup. These results support a state- and topology-aware view of optimizer quantization.

We introduce RS$^3$-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmentation (VOS) networks. Modern VOS models have converged on a common, expensive design: an image encoder produces a dense token grid for every frame, and a memory bank accumulates these tokens across all previously processed frames to condition future predictions. As a video grows longer, the resulting token budget governs both per-frame latency and peak GPU memory. Hence these models break on use cases such as --- long-form video or real-time deployment on memory-bounded accelerators. In this work we argue that the right axis along which to compress memory-bank VOS is the token budget itself. RS$^3$-Prune operates in two precise locations within an arbitrary memory-bank VOS pipeline: at the boundary between the image encoder and the memory-attention readout, where we restrict the queries that participate in the cross-frame attention to only a small, geometrically informed subset; and at the boundary between the memory encoder and the memory bank, where we restrict which tokens are ever permitted to enter the bank to those that lie within the object's spatial extent. Over various established benchmarks, RS$^3$-Prune delivers up to $38.8%$ FPS speedup and reduces $13.1%$ peak memory usage, while preserving a competitive $\mathcal{J}$&$\mathcal{F}$ compared to the unmodified VOS networks.

Automatically analyzing hours-long egocentric video is increasingly essential for progress monitoring, quality control, and safety in logistics, construction, and manufacturing. Yet current pipelines that process short, fixed-size windows with a vision-language model (VLM) are prohibitively expensive because cost scales with the number of model calls. To reduce this cost, prior work proposes triage policies to select which windows merit a VLM invocation. However, these policies either sample uniformly or rank windows using visual features, which ironically requires the video decoding that the budget constraints are meant to avoid. We propose audio-first triage: select windows using the lightest modality, scored before any video frame is decoded, so the approach composes naturally with token compression or quantization. The novelty lies in the objective, not the representation: rather than a per-frame sound-event detector, we train the selector to trigger once per action. This objective shift improves action coverage by 4.0-10.8 percentage points across all evaluated call rates, using frozen AudioSet-pretrained features without domain-specific sound-event labels. Using fewer than half of the available calls, the triage cuts 9-20% of VLM calls at matched coverage on EPIC-KITCHENS-100 (EK-100), surpasses uniform sampling through the mid-range on Ego4D over 247 clips, and outperforms two recent visual keyframe selectors. Code, the reference implementation and every results file this manuscript reads are at https://github.com/masjalayer/PreDecoding-AcousticTriage.

Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length increases. We identify two structural deficiencies in existing decoding methods as primary drivers of these failures: confidence-based scoring ignores decoded-neighbor support, and block partitioning prevents access to high-readiness semantic anchors, together causing tokens to be committed before their local context is sufficiently established. We propose \ours{} (Context-Aware Cluster Decoding), a training-free decoding method that scores each masked position by a multiplicative composite of softmax confidence and neighbor proximity, promoting contextually ready tokens above isolated candidates while suppressing low-confidence positional noise, operating block-free to keep high-readiness anchors globally accessible. \ours{} further applies architecture-aware calibration to handle confidence heterogeneity induced by diverse visual integration strategies. Experiments on three dMLLMs across four benchmarks demonstrate consistent quality gains and hallucination reduction over Original, with larger gains in several longer generation settings, highlighting the importance of neighbor support and visual integration strategy for future dMLLM decoding method design. Our code is openly available at https://github.com/zhaoyk-sysu/CACD-dMLLM.

Split Federated Fine-tuning (SFF) is a promising paradigm for scaling Large Language Models (LLMs) by partitioning model depth between resource-constrained clients and a centralized server. While system incentives for throughput and privacy favor deep partitions, the impact of such configurations on model utility remains poorly understood. In this work, we identify and characterize the Depth-Performance Dilemma: the regime that maximizes system efficiency is precisely where fine-tuning quality collapses. Through a comprehensive audit across four model scales (GPT-2 to Llama-3-8B) and diverse benchmarks, we demonstrate that deeper partitions provide monotonic gains in throughput and privacy at the cost of catastrophic performance plateaus. We evaluate a suite of state-of-the-art federated adapter aggregation methods including AVG, STACK, SVD, and FREEZE, revealing that while these techniques are effective in standard Federated Learning, they fail to mitigate the artifacts unique to split architectures. Finally, we provide a mechanistic diagnosis for this failure, tracing the collapse to the near-isometric topology of Transformers, which allows aggregation noise to propagate without attenuation until it triggers Attention Collapse in the server partition. Our findings challenge the prevailing assumption that partition depth is a utility-neutral tuning knob and provide a structural foundation for stable distributed LLM fine-tuning.

Deploying large language models on edge devices is increasingly limited by a widening gap between model size and available memory. Existing approaches such as quantization, smaller models, and offloading can raise the effective memory limit, but they still assume that the model can be compressed or partitioned to fit within some budget. We target the harder model-exceeds-memory setting, in which the model remains larger than resident memory throughout execution and storage becomes an active source of weights on the critical path. We observe that MLP activity during autoregressive decoding has strong temporal locality: approximately 82-85% of active neurons persist from one token to the next. This means that most sparse weights needed for the current token are already resident, and only the newly needed rows must be fetched from storage. We present NeuroPrefetcher, a storage-backed LLM inference system that exploits this property through predictive delta prefetching. After layer 0, a single GPU-resident predictor, occupying 2.86% of base model parameters, predicts sparse activity for all downstream MLP layers in one forward pass. The runtime compares these predictions against resident GPU buffers and issues application-scheduled NVMe reads only for incoming delta rows, replacing reactive operating-system demand paging with explicit, model-aware weight movement. On real unified-memory edge hardware, NeuroPrefetcher achieves 7.9-12.0x speedup over llama.cpp across constrained memory budgets.

As the use of Artificial Intelligence (AI) and Large Language Models (LLMs) is becoming common in everyday applications, their ability to interpret natural language has increased significantly. An emerging application of AI is integration with network management and orchestration practices. An instance of this integration is LLM-enhanced intent-based networking, where network operators will control a network using natural language. This work presents the use of dynamic routes with a semantic router to identify an intent from a network operator's prompt and extract necessary details for intent fulfillment in intent-based 5G+ core networks. Furthermore, the performance of static route selection is assessed by evaluating multiple encoders and dynamic route detail extraction accuracy against a series of realistic operator prompts. The presented results show that static and dynamic routes are successful in detail extraction and schema formatting.

Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of each claim in their outputs. We introduce Kernel Token Contradiction (KTC), a lightweight approach to compute claim-level UQ under realistic white-box conditions. KTC represents the candidate tokens involved in LLM generation as a positive semi-definite kernel that integrates both the LLM's conditional distribution and a token contradiction score. We then use the Von Neumann entropy to quantify the uncertainty of this kernel. To estimate token contradiction, we develop a new approach based on frequency statistics from the Wikipedia corpus. Although CPU-only, our approach achieves over an 8.2x speedup compared to state-of-the-art GPU-accelerated methods based on cross-encoders, and over a 65x speedup compared to CPU-only methods with comparable performance. Our evaluation spans two benchmarks across four European languages and 16 different models. KTC not only matches the average performance of existing methods but also outperforms them in high-precision regimes. This combination of computational efficiency and accuracy makes real-time monitoring of LLM outputs practical in production.

The rapid evolution of hybrid large language models (LLMs), which interleave grouped-query-attention (GQA), state-space model (SSM), and Mixture-of-Experts (MoE) layers, introduces two fundamental challenges for near-memory processing (NMP) architectures. First, the Technology Wall: the conventional 6F^2 DRAM cell is approaching its physical scaling limits at 10nm-class nodes, making it difficult to meet the memory capacity demands of MoE models with hundreds of experts. Second, the Architecture Wall: existing NMP designs target narrow arithmetic intensity (Op/B) ranges and cannot efficiently support the heterogeneous compute characteristics of hybrid LLMs, spanning memory-bound SSM layers, compute-intensive GQA layers, and large Op/B variations across experts. We propose NOVA, a technology-architecture co-designed NMP system that overcomes both walls. On the technology side, NOVA combines a 4F^2 vertical channel transistor (VCT) DRAM cell with a peri-over-cell (POC) structure to achieve approximately 2x memory density at iso-area over conventional 6F^2-based DRAM, enabling continued scaling into sub-10nm nodes. On the architecture side, NOVA repurposes the POC peripheral-die (peri-die) to host processing units, forming a 2-tier NMP architecture: Tier-1 (peri-die NMP) for low-to-mid Op/B operations, and Tier-2 (base-die NMP) for mid-to-high Op/B operations. Parallel execution across tiers supports diverse compute patterns for hybrid LLMs, maximizing inference performance. Evaluated on state-of-the-art hybrid and MoE LLMs including Nemotron3-Nano, Nemotron3-Super, Falcon-H1R, and Qwen3, NOVA achieves on average 4.5x higher throughput, 69.8% lower end-to-end latency, and 5x better energy efficiency over a GPU baseline, with only 3.9% area overhead and no loss in memory capacity.

Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is misaligned with factual correctness. Response-level confidence is a coarse signal: a single generation can mix correct and incorrect statements, so a single number is not actionable for users that must accept, reject, or verify individual pieces of information. We study claim-level confidence calibration as a decision-relevant uncertainty signal: each response is decomposed into atomic, verifiable claims, and each claim is assigned a calibrated confidence using inference-time signals from consistency across samples and self-verification. Our framework operates in closed-box settings (no logits, no fine-tuning) and applies post-hoc calibration directly at the claim level, enabling selective intervention such as evidence retrieval or human review for low-confidence claims. Across TriviaQA and TruthfulQA we evaluate seven baselines on six recent models (Llama-3.1, Mistral, Qwen2.5, DeepSeek-R1, GPT-4, GPT-4o), and show that claim-level decomposition combined with post-hoc calibration reduces expected calibration error on factual questions while exposing failure modes on adversarial false-premise questions where decision-makers most need reliable uncertainty estimates.

Two-stage neuro-symbolic architectures provide an elegant paradigm for visual problem solving by cleanly separating connectionist perception of predefined symbols from possibly later defined relational reasoning thereon. However, anchoring high-level predicates into visual frames typically necessitates annotations that are expensive to acquire. In this work, we introduce the Dynamic Orthogonal Concept Bottleneck (D-OCB), an object-centric slot- VAE framework designed to extract human-aligned symbolic predicates under extremely weak supervision. D-OCB eliminates the arduous manual tuning of loss-balancing coef- ficients by dynamically learning optimal hyperparameter allocations during training. To infuse prior knowledge on independence of concept categories, in addition to standard re- construction self-supervision we penalize correlation across concept subspaces. Crucially, to combat the instability of very low supervision regimes, D-OCB incorporates a dynamic di- mensionality allocation mechanism; this adaptive formulation allows well-represented con- cepts to yield latent dimensions to underperforming concepts that are lagging behind, effectively preventing representation collapse and significantly improving overall concept accuracy. Through an extensive empirical evaluation, we demonstrate that our framework achieves high concept alignment and downstream visual reasoning accuracy using minimal label budgets, matching or outperforming end-to-end paradigms.

Interpretability research increasingly asks when concepts emerge during training and whether linear probes recover real structure, but in language models these claims are hard to validate because language offers little ground-truth ordering of concepts or relationships among them. We propose the use of astronomical ground truth through AstroPT, a transformer trained on millions of galaxy images, as a calibration testbed. AstroPT is an LLM-like model trained within a domain where the difficulty ordering of concepts and the relations among them are known in advance. Probing frozen representations across checkpoints, layers, model sizes, and objective choices, we find that galaxy properties emerge in a fixed order that tracks their known difficulty---quantities written almost directly into the pixels (band magnitude) become decodable early in training and shallow in the network, while multiband/spectra based and inferred quantities (such as redshift and specific star formation rate) emerge later and deeper. This order is invariant to our tested training objectives, and scales in magnitude but not in sequence with capacity. Our linear probe directions further recover the known physical structure among galaxy properties. Our findings suggest that astronomy offers a controlled sandbox for calibrating mechanistic interpretability methods we otherwise apply to LLMs blind.

Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their communicative behavior across contexts. Despite recent advances in equipping Large Language Models (LLMs) with social understanding capabilities, existing approaches often model culture as a static demographic attribute, limiting their ability to accommodate hybrid and dynamically expressed communicative preferences. Therefore, in this paper, we propose DyCAC, a training-free framework that achieves fluid social alignment by incorporating \underline{Dy}namic \underline{C}ultural \underline{A}daptation with continuous \underline{C}ognitive tracking. Rather than inferring a fixed cultural identity, DyCAC models culturally relevant communicative preferences as a time-varying mixture of population-level cultural reference profiles. This reference-based representation is further calibrated using dialogue-style signals observed in the ongoing interaction, enabling the model to capture both composite cultural influences and turn-level shifts in communicative behavior. In parallel, a memory module driven by Theory of Mind (ToM) continuously tracks the cognitive states of the interlocutor. Extensive experiments on interactive social and cultural benchmarks demonstrate the superiority of our approach. The proposed framework outperforms existing baselines, exhibiting enhanced social intelligence and broad adaptability across varied multicultural contexts.

Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the model continues to recompute tokens that are already stable. To address these limitations, we propose CAI-DLLM, a training-free inference method that uses first-step confidence to guide denoising and reduce inference time. Specifically, CAI-DLLM commits easy tokens earlier, allocates more denoising steps to harder tokens, and adjusts decoding schedules across output blocks. As it relies only on first-step confidence signals, it does not require retraining, extra predictors, or weight updates. We evaluate CAI-DLLM on LLaDA-8B-Instruct and Dream-7B-Instruct across math, code, reasoning, commonsense, and long-context tasks. CAI-DLLM achieves up to 18.2x wall clock inference speedup on LLaDA GSM8K while improving accuracy from 76.27% to 77.41%, and up to 13.1x speedup on Dream HumanEval while achieving higher pass@1 than no-cache inference, 48.17% compared with 46.95%. On harder reasoning tasks, speedups reach 44.8x, with a largest accuracy drop of 4.4 points, while energy consumption is reduced by up to 95.3%.

Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such feedback introduces two manipulation directions: whitewashing hateful content as normal and smearing normal content as hateful. This study examines the susceptibility of initially correct model judgments to annotator-style rebuttals and analyzes whether attack effectiveness differs across manipulation directions. We introduce a rejudge protocol that extends direct contradiction with decision-boundary perturbations and adversarial rationales. Experiments with multiple LLMs on two hate speech datasets show that annotator-style rebuttals substantially degrade moderation performance, with stronger effects in multi-turn settings. The results further reveal stable, model-specific asymmetries between whitewashing and smearing across attack configurations, indicating distinct directional vulnerability patterns. Explicit reasoning prompts and defensive instructions reduce these effects but do not eliminate them. These findings highlight the need for direction-aware safeguards and dedicated feedback-robustness evaluation in human--AI moderation workflows.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer to fused cross-modal representations, leaving multimodal inputs exploitable through latent semantic cues. We propose Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space. TA-SPA integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals, with Semantic-Preserving Augmentation (SPA), which diversifies harmful target anchors while preserving semantic consistency. Experiments show strong attack effectiveness and transfer to commercial MLLMs, with competitive performance under representative defenses. Additional controls and probing support the intended factorization without implying perfect disentanglement, motivating representation-level safety alignment beyond input-level filtering.

Evaluation of large language models (LLMs) increasingly requires predicting how a model will perform on new questions or tasks before collecting large amounts of new annotations. This problem is challenging because question difficulty, scenario, and underlying capability demands can vary substantially. Simple retrospective averages may confound model ability with item characteristics. In this paper, we study a model-based evaluation framework that combines multidimensional item response theory model with question contexts to predict LLM performance on unseen questions. The framework represents LLMs through latent capability profiles while using question content to inform item characteristics, allowing information to transfer beyond previously observed items. Empirically, we find that for within-scenario evaluation, incorporating question embeddings improves prediction relative to model-free baselines, and that multidimensional latent structure provides a richer description of capability variation than unidimensional alternatives. At the same time, our results reveal an important limitation that the generalizability does not necessarily translate into reliable prediction under cross-scenario shift. These findings suggest that context-aware psychometric modeling is a promising direction for efficient and interpretable LLM evaluation, while also highlighting cross-scenario generalization as a central open challenge.

Large language models generate tokens sequentially, but can they execute multiple tasks concurrently while forming each token? Broader attention allocation may provide a mechanism for such task concurrency. Existing approaches to scaling inference primarily rely on longer generations, more samples, or additional verification stages, while attention dispersion is often treated as a signal of interference or error. Task concurrency within serial generation therefore remains underexplored. We propose the Model Hyper-Threading Hypothesis and evaluate its predictions using multiple coordinated tasks that share state within the same problem. We design three conditions (Baseline, Serial Functional Scheduling, and Concurrent Functional Loading) and evaluate their benefits and costs using accuracy, output-token distributions, and attention metrics. On an AIME 2025 development set, Concurrent Functional Loading achieves the highest accuracy. Relative to Serial Functional Scheduling, its typical output length is similar and it is shorter on most problems, while exhibiting greater attention dispersion and higher task-relevant coverage, albeit with a heavier output-length tail. Within-step concurrency and its causal mechanism still require direct tests. Our results show that more dispersed attention can coexist with higher accuracy, providing preliminary behavioral and correlational evidence for the hyper-threading hypothesis. These findings motivate a shift in perspective on inference scaling from "generating more tokens" toward "having each generation step carry more tasks," pointing to a new avenue for improving reasoning performance.

Large Language Models (LLMs) demonstrate remarkable problem-solving capabilities when guided by Chain-of-Thought (CoT) prompting, yet the internal mechanisms underlying these improvements remain poorly understood. In this work, we investigate where CoT-related causal effects emerge across the generated reasoning trajectory and which attention heads carry signals that contribute to final-answer computation. Because CoT reasoning unfolds over multiple generated tokens, standard activation patching at a single static token position is insufficient to characterize these temporally distributed effects. To address this limitation, we introduce a sequential activation patching framework that traces CoT-conditioned attention-head activations across token positions and aggregates their effects using Part-of-Speech-guided analysis. We further introduce Sequential Multi-Head Patching to evaluate the joint contribution of distributed head sets, together with cross-question and random activation controls. Targeted zero-ablation experiments show that the identified heads are functionally important for successful answer generation and affect several overlapping mechanisms, including reasoning-trajectory maintenance, answer anchoring, exemplar-target separation, and numerical generation. Overall, our results provide evidence for distributed reasoning-support sub-circuits associated with CoT-conditioned computation.

Cubic regularized Newton methods have the optimal $\mathcal{O}(ε^{-3/2})$ global rate, but a dense subproblem solve limits the feasible block size. Scalable Cubic Newton variants replace the true block curvature with a diagonal, low-rank, Kronecker-factored, or sketched surrogate and, most often, give up the exact cubic step. We introduce a blockwise optimizer that minimizes an independent cubic model per parameter tensor over the true block Hessian, under a per-block adaptive cubic constant and a monotone guard on the full loss. Arbitrarily large tensors are handled matrix-free in a Lanczos-built Krylov subspace, where we prove that the step minimizes the cubic model. The theory also supplies the $\mathcal{O}(ε^{-3/2})$ iteration complexity bound, a second-order guarantee, and monotone per-block descent. Four variants of this outer scheme are evaluated against the original adaptive regularization with cubics (ARC) optimizer, some other recent cubic Newton variants, Adam, SOAP, and L-BFGS. On a 91.4M-parameter implicit neural representation (INR), the variants introduced in this work are the only evaluated here cubic Newton methods whose steps stay exact on every block. Run to full convergence on FINER 2D image fitting, one of the ARC variants introduced here, ARC-$\varphi_1$, reaches 133.5 dB peak signal-to-noise ratio, while tuned Adam plateaus at 78.2 dB after about 70 minutes. In that time ARC-$\varphi_1$ reaches 95.6 dB.

Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, but do not test this particular receipt-, scope-, and closed-replay design at the COMPLETE boundary across controlled termination faults. W e instantiate and evaluate Evidence-Carrying Termination (ECT): an agent may return COMPLETE only when a typed certificate binds every required answer claim to valid, in-scope trace evidence and a deterministic replay reconstructs the claimed value. A locked static study crosses 48 ful ly synthetic tasks in six tool-use families with clean execution and eight faults. ECT produced 0/288 unsafe completions versus 252/288 for the inspected termination-critic core (difference -87.50 pp, 95% task-cluster interval [-87.50, -87.50] pp). A fresh, prespecified and frozen 576- trajectory study then compares ECT with the critic core, its faithful controller, and a full-trace LLM critic. On 22 primary held-out task clus ters, ECT produced 0/66 premature unsupported terminations versus 40/66 for the controller (difference -60.61 pp, 95% interval [-78.79, -40.91] pp), while supported completion was 97/132 versus 92/132 (difference 3.79 pp, interval [0.00, 9.09] pp), satisfying a -10-point noninferiority margin. ECT executed successful recovery in 18/66 trajectories, of which 17 subsequently completed with support; all three closed-loop gates p assed. ECT certifies support in a recorded trace under declared assumptions, not external truth, safety, or alignment.

Text-to-image (T2I) diffusion models offer powerful visual generation, but their controllability creates a critical safety challenge: adversarial prompts can steer the denoising trajectory toward policy-violating content such as explicit nudity or graphic violence. Existing safeguards mostly act before generation through prompt filtering or after generation through image classification, leaving the diffusion process itself unguarded and often yielding only refusal rather than safe visual repair. We introduce GuardPaint, a speculative decoding framework for safe T2I generation that intervenes inside the diffusion trajectory without modifying the base model. A lightweight auditor monitors intermediate images, localizes unsafe regions, and triggers surgical inpainting repair only where needed. Candidate repairs are generated by a policy-aligned inpainter and selected through a guarded tournament that accepts edits only when they improve policy compliance while preserving prompt fidelity and perceptual quality. Across five jailbreak families SneakPrompt, MMA, PGJ, DACA, and RABell and UNet/flow-matching models including SD~1.5, SDXL, SD~3.5, and FLUX.1-dev. GuardPaint reduces attack success and harmful generations with minimal degradation to image quality, prompt fidelity, and benign behavior. Content warning: This paper contains examples involving nudity and violence that some readers may find disturbing, distressing, or offensive.

Multimodal large reasoning models often rely on long Chain-of-Thought (CoT) traces in which a substantial fraction of tokens, such as repeated visual descriptions, self-reflection, and other visually-disengaged filler, inflate inference cost without contributing to the answer. Existing CoT compression methods optimize output length but never measure whether a reasoning token is actually grounded in the image. We propose VIG (Visual Information Gain), an information-theoretic GRPO reward that scores each reasoning token by how much the image reduces its predictive uncertainty. VIG is computed online from two forward passes of the same policy, one with and one without the image, so no reference chains, external annotations, or auxiliary reward models are needed. Across six main multimodal reasoning benchmarks and three Qwen3-VL-Thinking model sizes (2B/4B/8B), plus an additional R1-Onevision-Bench evaluation on 8B, VIG consistently improves the accuracy--efficiency trade-off, supporting our central claim: efficient multimodal reasoning emerges from raising visual information density, where every reasoning token earns its place by anchoring to the image, rather than from imposing a length budget. Our source code is available at https://github.com/chaser682/vig.

Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in interaction trajectories are largely discarded after a single policy update. Existing experience-augmented approaches retrieve historical guidance at inference time, but they apply experiences without accounting for the policy's evolving capability and create persistent dependencies on external retrieval. We propose EDGE (Experience-Distillation for Guided Exploration), a framework that treats retrieved experiences as temporary training-time scaffolds and progressively internalizes their benefits into the parametric policy. Concretely, EDGE partitions each rollout group into experience-conditioned and experience-free trajectories to estimate and admit only positive marginal gains without extra sampling, then distills the induced behavior into the base policy via a reverse-KL objective on its own empirical support. A co-evolutionary experience bank further synthesizes guidance from emerging failure modes and prunes obsolete entries as the policy evolves. Across embodied, web, and search-based QA tasks, EDGE improves over strong RL baselines by up to 12.5 points and remains effective without inference-time scaffolds or a proprietary reflector. The code is available at https://github.com/xvolcano02/EDGE.