每天知道
你的领域
出了什么

Generative molecular models for drug design are a promising direction with much active research. In the next phase of computational drug design, such models will need to understand small molecule structure and protein-ligand interactions, and they will need to possess the machinery to generate molecules de novo. Incorporating each feature poses a critical challenge. Equally important, yet often treated as secondary, is the ability to grow a molecule from a partial starting point — a scaffold or fragment supplied by a chemist — which is the central operation of lead optimization. We present Sesame (Spatial Evoformer for a Structure-Aware Molecular Engine), a diffusion-based molecular generation model that leverages a novel spatial pairformer module to condition on partial molecular structure and the surrounding protein pocket, both expressed as continuous spatial density maps. This single conditioning mechanism supports both de novo generation and fragment-conditioned lead optimization, letting a medicinal chemist prune a hit to a scaffold and have Sesame grow it in productive ways. In addition to this module, we also introduce a diffusion framework for joint denoising of atom types, bond types, and positions, along with a trajectory finetuning scheme that trains on the model's own sampling rollouts to improve generation quality. Sesame is trained on a large corpus of ligand-only and protein-ligand datasets.

On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck. Existing systems primarily optimize for decoding speed, implicitly assuming that faster execution is always preferable. We show instead that on-device LLM inference often has exploitable configuration slack: modestly lowering NPU and memory frequencies preserves quality of experience (QoE) while substantially improving energy efficiency and reducing heat. Realizing this opportunity in production is challenging. The most energy-efficient NPU/DDR setting varies with the model, inference engine, platform, and runtime conditions, with no stable ranking across configurations. Commercial devices further lack component-level power sensing, and shell temperature evolves with request arrivals, response lengths, and thermal history. To address these challenges, we propose EnerInfer, the first on-device LLM inference framework that jointly manages energy efficiency, throughput, and thermal comfort for LLM workloads. EnerInfer replaces per-model profiling and sensor-heavy control with disaggregated, model-structure-aware prediction and ranking-driven online feedback. It predicts throughput and power for unseen LLMs across NPU/DDR frequency settings, selects QoE-satisfying efficient configurations under runtime interference, and uses lightweight limited-horizon thermal prediction to dynamically switch between energy-optimized and thermally constrained inference. Evaluations on real-world LLMs show that EnerInfer improves energy efficiency by up to 65%, 12%, and 24% on phones, a laptop, and a development board, respectively, without QoE violation.

Recent advances in quantum machine learning have motivated efficient models for sequential data processing. In this paper, we propose Self-Modulating Quantum Fast Weight Programmers, or Self-Modulating QFWP, which extends Quantum Fast Weight Programmers by introducing adaptive modulation over both newly generated fast-weight updates and historical fast-weight memory. Numerical results show that the proposed mechanism improves convergence stability and prediction performance across varying model settings, including different numbers of qubits and input sequence lengths. We further provide theoretical arguments explaining how self-modulation balances new information injection with memory retention, thereby enhancing temporal information propagation. These results suggest that Self-Modulating QFWP is a compact and effective framework for quantum machine learning on time-series data.

Reviewing recorded interviews for affective cues such as composure, hesitation and agitation is slow and subjective, and cloud services that could automate it require sensitive audio to leave the device. EmotionAI is a fully local Computational Intelligence (CI) pipeline that couples Speech Emotion Recognition (SER) with generative reasoning. Speaker diarisation, Whisper Automatic Speech Recognition (ASR) and a wav2vec2 emotion classifier produce per-segment affective evidence, which is then passed to an adversarial three-model local Large Language Model (LLM) panel for timestamp-grounded and citation-constrained question answering. Zero-shot evaluation on the RAVDESS four-class English subset (n = 672) exposes cross-corpus fragility rather than classifier superiority: the deployed classifier scores 48.8% accuracy, above random (24.9%) and majority (28.6%) baselines but below an in-domain MFCC + logistic-regression comparator (71.0%). The complete pipeline runs in a mean 157 s on CPU (real-time factor approximately 1.33) with zero external calls. The contribution is not state-of-the-art SER but an auditable, privacy-preserving integration of imperfect affective evidence into grounded conversational analysis, together with an honest empirical account of where cross-corpus transfer and human-centred validation still fall short.

Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.

Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade during continuous consolidation. However, existing research assumes memories are derived from unbiased experiences. In this work, we identify and formalize a novel phenomenon: Memory Contagion — the cross-temporal propagation of evaluator bias through agent memory. We show that when agents are trained or guided by biased evaluators, their experiences become biased; when these trajectories are stored and consolidated into memory, the bias propagates to future agents retrieving from the same memory store, even when consolidation is perfect (oracle). Across two bias types (length preference, authority bias) and four experimental phases, we demonstrate: (1) Memory Contagion occurs for length bias even with perfect consolidation on older models (Gamma_A = 13.18, DeepSeek V4-Chat), while newer models (V4-Pro, Claude) are immune, proving both that biased input is a sufficient cause and that contagion is model-generation-dependent; (2) authority bias fails to propagate in all 15 controlled multi-seed experiments (Gamma_A = 0.00), revealing that not all evaluator biases can cross temporal boundaries through current memory architectures; (3) No observed safe threshold: length bias propagation is detected at contamination rates as low as p=0.2. Our findings expose a critical but contingent vulnerability in current agent memory designs and provide formal tools for measuring cross-temporal bias propagation.

The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems. The book covers the full stack from first principles to production deployment, organized around a central thesis: building great agentic systems requires understanding every layer of the pipeline, not just one. The book opens with the LLM substrate — transformer architecture, GPU systems, training and fine-tuning (SFT,LoRA, MoE), model compression, and inference optimization — treated as essential foundations rather than the primary focus. It then develops the alignment and reasoning layer: reinforcement learning from human feedback (RLHF), PPO, DPO and its variants, GRPO, reward modeling, and RL for large reasoning models including chain-of-thought and test-time scaling. The second half is devoted to agentic AI proper. Topics include agentic training and trajectory-based RL, retrieval-augmented generation (RAG and Agentic RAG), memory systems (in-context, external, episodic, and semantic), agent harness design and context management, and a taxonomy of agent design patterns. Inter-agent coordination is covered in depth: the Model Context Protocol (MCP), agent skills and tool use, the Agent-to-Agent (A2A) communication protocol, and multi-agent architectures spanning centralized, decentralized, and hierarchical topologies. The book concludes with agent development frameworks, agentic UI design, evaluation methodology for agentic tasks, and production deployment. Each chapter pairs rigorous theoretical foundations with implementation guidance, code examples, and references to the primary literature.

Vector-scalar comparison is a fundamental computation primitive that compares each element in a vector against a single scalar value. It is widely used in various data-intensive workloads from databases to machine learning. Due to its low computational intensity, its execution tends to be memory-bound, limiting the utilization of compute resources. Processing-using-DRAM (PuD) is an emerging computing paradigm that performs massively parallel bitwise operations directly inside DRAM arrays, alleviating off-chip data movement. Existing PuD-based approaches require many DRAM commands because the comparison's algorithmic complexity grows with operand bit-width in the bit-serial execution model. This command overhead becomes the dominant bottleneck, limiting application-level speedup. We propose Clutch, a data representation and comparison algorithm that accelerates vector-scalar comparisons in PuD systems with high efficiency and scalability. Clutch first uses temporal coding, encoding each vector value as a sequence of leading ones, which enables lookup-based comparison against a scalar by accessing the corresponding DRAM row. To avoid the prohibitive memory footprint of lookup tables at high precision, Clutch partitions operands into multiple multi-bit chunks, compares chunks independently using compact lookup tables, and merges the per-chunk results with a PuD-efficient procedure. By adjusting the number of chunks, Clutch provides a flexible tradeoff between throughput and memory usage. Across predicate evaluation and decision tree inference, Clutch improves end-to-end application throughput and energy efficiency by an average of 12x and 69x over highly optimized CPU and GPU execution, and by 2.9x and 3.0x over the state-of-the-art bit-serial PuD implementation. We also present the first mapping of decision tree inference to PuD execution, extending PuD to a new application domain.

The rise in GPU compute speed has outpaced improvements in host-to-device memory transfer speeds, despite the advent of shared-memory superchips. Consequently, memory transfer times now constitute an increasingly large fraction of total time-to-solution, compelling developers to compress GPU kernel input and output data into compact, minimal formats prior to GPU-offloading. This complements existing work on GPU- and compute-friendly data arrangements. We study a Smoothed Particle Hydrodynamics solver and propose memory layout strategies for host-side particle data that are particularly well-suited to GPU-offloading. Specifically, we advocate splitting classic array-of-struct data structures into a split array-of-struct arrangement, in which each logical struct decomposes into substructs determined by kernel read/write access patterns and attribute types. Splitting a monolithic particle struct into several bespoke, finer-grained structs can reduce the time required to pack data to and from buffers by ~20% - 40%, lowering total time spent on GPU-offloading by ~12% - 25%.

In this work, we propose Frontier-based Path Planning with Adaptive Sampling (FPAS), a novel framework designed for efficient goal-reaching in large-scale, unknown environments. While existing planners often struggle with computational bottlenecks or inefficient paths during long-range navigation, FPAS overcomes these challenges by reinterpreting the frontier concept for goal-directed tasks. Specifically, our method leverages frontiers to effectively guide forward progression into unobserved regions and to select promising subgoals for backtracking from dead-ends or inefficient paths. Furthermore, FPAS introduces an adaptive sampling mechanism based on a frontier-derived openness metric. This mechanism dynamically adjusts the global graph's density by employing sparse nodes in open areas to alleviate computational burdens, while preserving denser sampling in narrow passages to ensure connectivity. Extensive evaluations demonstrate that FPAS substantially improves computational efficiency over baseline methods while maintaining highly competitive goal-reaching performance.

Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query. When experiences are compressed into reusable fragments, memories from different situations may appear equally relevant if they involve recurring entities or user states. We refer to this failure as context collapse: memories lose the surrounding context needed to judge whether they provide valid evidence for the current query. To address this problem, we propose Contextual Reinstatement for Agentic Memory (RaMem), a framework that turns retrieved memory fragments into contextually verifiable evidence. RaMem operates through four coordinated stages: (i) evidence anchoring grounds each memory in its original episodic conditions, especially event time, mention time, session span, and participants; (ii) recall condition induction derives the evidence conditions implied by the query; (iii) validity-aware retrieval uses these conditions to prioritize context-compatible memories while retaining content-relevant candidates as fallback evidence; and (iv) context-preserved synthesis keeps the selected memories' structured context available to the generator. Experiments on long-term memory benchmarks show that RaMem consistently improves performance over strong memory baselines, with average F1 gains of more than 10% across several backbones.

LLM agents increasingly act as personal assistants that must remember a user's profile over months: who they are (attributes), what they routinely do (habits), and what they prefer (preferences), and keep it updated as jobs, routines, and tastes drift. Existing benchmarks evaluate this "memory" ability through short, simplified interactions, missing three core properties of real behavior: the profile is heterogeneous, with attributes, habits, and preferences evolving on different timelines; changes are driven by external context such as seasons and life events; and evidence is rarely stated explicitly, instead scattered across many small actions in different apps that a memory system must infer from. We introduce DynamicMem, a synthetic benchmark that constructs 15 months of activity per user, providing long-term multi-app data that real users' privacy keeps out of reach. It provides user-consistent trajectories averaging 2.2M tokens and 1,772 grounded events per user across 16 applications such as e-commerce, fitness, and social platforms. The profile evolves over this period and is never given explicitly: each attribute, habit, or preference must be inferred from small signals scattered across apps. We evaluate at five quarterly checkpoints to track how systems scale as history grows. Benchmarking five representative systems exposes problems a single accuracy score hides: (i) profile reconstruction degrades with history length while service-task accuracy stays flat, despite both drawing on the same memory; (ii) no system both keeps facts that stay true and replaces facts that change, with errors clustering on preferences and on naming the exact referent; and (iii) over 93% of failures trace to what the memory retrieves, not to the model writing the answer, so the largest room for improvement lies in memory itself. Code: https://wenyaxie023.github.io/DynamicMem/

Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remains challenging. Existing methods often retrieve only local fragments and fail to recover the broader task-relevant context needed for complex repository-level tasks. We present DeepDiscovery, a task-level repository-understanding method for large industrial codebases. DeepDiscovery uses a two-stage Location--Inference framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints. Across controlled method-level evaluation, organization-internal industrial repository-understanding scenarios, and end-to-end evaluation on SWE-bench Verified, DeepDiscovery consistently improves task-relevant file recovery and downstream SE performance. On 27 medium-scale tasks, DeepDiscovery achieves the best file recovery quality among five representative baselines without offline preprocessing. On organization-internal industrial tasks from a production-scale integrated codebase ecosystem, including 27 medium-scale tasks and 40 large-scale tasks, DeepDiscovery improves Full Recall Rate across multiple AI coding systems, with absolute gains ranging from 1.6 to 9.2 percentage points on large subprojects and from 2.5 to 7.4 percentage points on medium-scale subprojects. In a controlled end-to-end evaluation on SWE-bench Verified, a system equipped with DeepDiscovery achieves a 78.6% Solve Rate, outperforming the corresponding baseline by 8.2 percentage points. These results suggest that stronger task-level repository understanding can improve coding-agent performance on complex SE tasks.

Vine robots, a class of soft, growing robots, are suitable for navigating complex and confined environments due to their compliant bodies and self-supporting growth mechanism. However, hysteresis, tether interactions, and deformations make them difficult to predict and model, which in turn limits the effectiveness of conventional planning and control approaches. In this work, we present a data-driven, vision-based control framework for the first autonomous vine robot system. Our system integrates 19 cameras distributed along the robot's body to provide comprehensive feedback of both the robot state and the surrounding environment. Using this rich whole-body vision feedback, we train an end-to-end visuomotor policy from demonstrations for closed-loop autonomous control in complex environments. The policy efficiently aggregates information from distributed sensing while maintaining robustness to inaccurate robot states and actuation. Experimental results demonstrate that the learned policy enables robust navigation and manipulation in challenging scenarios, including steering through branched structures, climbing up slopes, traversing unsupported terrain, reaching objects precisely, and maneuvering through confined spaces and obstacles. Project website https://panovine-bot.github.io

Transformer language models have become established tools for modeling human sentence processing, with measures such as surprisal and attention entropy serving as effective predictors of reading difficulty that together capture complementary aspects of processing load. Here, we explore a related class of transformer models: energy-based transformers, which provide a principled formal link to associative memory models, bringing processing research into direct contact with the broader literature on Hopfield networks and dense associative memory. To our knowledge, this is the first exploration of an energy-based transformer measure in computational psycholinguistics. Across reading-time corpora (Natural Stories, UCL eye-tracking, UCL self-paced reading), the energy measure is a robust predictor of reading times, providing significant fit beyond surprisal in all three. In a controlled experiment on relative clause processing, energy at a single layer captures the well-known object/subject asymmetry. We find evidence that it subsumes effects attributable to both attention entropy and surprisal, suggesting that energy may serve as a single unified predictor where multiple complementary measures have previously been required.

Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly across depth. This is a default inherited from the original transformer and largely unchanged since, yet a growing body of evidence suggests that layers contribute non-uniformly to the final output, with later layers refining the residual stream rather than transforming it. We ask whether parameter capacity should reflect this asymmetry. Our controlled experiment shows that, under a fixed budget, allocating more capacity to earlier layers and less to later layers improves perplexity over a uniform-width baseline, while the reverse allocation hurts. Building on this result, we introduce Tapered Language Models (TLMs), an architectural principle in which a parameter-bearing component is monotonically tapered across depth under a fixed total budget. MLPs are the natural site for this instantiation: they dominate parameter count across all modern LM families and expose width as a single, clean axis of variation. Across three model scales and four architectures (Transformer, Gated Attention, Hope-attention, and Titans), tapering MLP width via a smooth cosine schedule consistently improves perplexity and downstream benchmark performance over uniform baselines, at no additional parameter or compute cost. These findings establish depth-aware capacity allocation as a simple, architecture-agnostic axis of language model design, a free lever hidden in plain sight.

Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inference stream. Existing methods all share the same template, a per-step direct-attention score followed by deterministic top-$K$ selection, which converts a single below-cutoff step into an irreversible verdict and permanently erases any subtly important token that direct attention cannot single out from noise. To address this challenge, we propose Nexus Sampling, a training-free eviction method that pairs Nexus scoring, an iterative walk over direct attention that surfaces bridge tokens, with weighted reservoir sampling, which retains tokens with inclusion probability in place of deterministic top-$K$. Theoretically, we show that Nexus Sampling dominates deterministic top-$K$ in long-run survival of subtly important tokens. Empirically, at 80% KV cache eviction, Nexus Sampling matches dense attention within 1% on LongBench while outperforming top-$K$ baselines on retrieval-heavy tasks, with up to 10x smaller per-sequence cache memory.

We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy also reduces end-to-end latency: median response time is 2,026 ms versus 3,698 ms for Native Opus — a 1.83X speedup at p50 — because the SKIPPED path (DeepSeek only, no Opus call) dominates the workload distribution. Quality matches or exceeds the Opus baseline: 100% pass rate on a 20-task Code/Math/Instruct benchmark versus 95% for Native Opus. We further describe a rule-based complexity router that selects the SKIPPED path for simple agentic turns and a hybrid tool-call strategy that bypasses the speculative pipeline for schema-critical tool-selection turns. RLM-Cascade is deployed in production as an enterprise AI infrastructure component and published as open source with a live metrics dashboard and Prometheus endpoint.

Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train--deployment prompt mismatch. For within-benchmark self-improvement, ToolGraph combines schema-derived topology, transition weights estimated from successful rollouts, and history-aware controls for write prerequisites and repeated-search loops. We then construct 161 preference pairs by locating divergence points via state-based matching and prefix-based alignment, filtered through action-correctness annotations, and train DPO under the same ToolGraph context used at inference. Across 375 tau2-bench tasks, ToolGraph raises the weighted average reward from 0.304 to 0.338 (+11.2% relative), while ToolGraph+DPO reaches 0.355 (+16.8% over the baseline), with the DPO gain concentrated in airline and retail. Fine-grained diagnostics further show that roughly half of telecom trajectories exhaust the step budget before action execution and that chosen reward positivity is the most useful checkpoint signal across our 16 evaluated DPO configurations.

LLM agents are increasingly deployed in multi-party environments, handling sensitive personal data on behalf of individual users, for instance in group chats. When such an agent discloses private information, it reaches every group member at once. This risk is structurally harder to control than in one-to-one settings, as every piece of private information must be appropriate for every recipient in the group. Yet all existing contextual privacy benchmarks consider only single-interlocutor settings, leaving multi-party privacy risks unmeasured. We introduce MuPPET (Multi-Party Privacy Exposure Testing), a benchmark for contextual privacy in multi-party conversations. Our experiments show that models leak substantially more in multi-party settings than one-to-one evaluations suggest. Frontier models are vulnerable, and smaller open-weights models, often preferred for local deployment with sensitive data, even more so. Existing contextual privacy defences offer only partial protection, degrade utility, and do not resolve the underlying party-tracking problem.

Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabilities, yet data contamination inflates reported performance and undermines fair comparison. Existing decontamination methods are evaluated solely through aggregate accuracy, which can obscure substantial differences in per-sample model behaviour, and many require access to an uncontaminated model. In this paper, we propose a sample-level evaluation framework for decontamination that complements accuracy-based assessment with distributional distance metrics, measuring how closely a decontaminated model recovers the output distribution of an uncontaminated model on each sample. Building on this framework, we introduce Uncertainty-Based Decontamination (UBD), a family of methods that leverage deep ensembles of the contaminated model to estimate per-sample memorization without requiring a uncontaminated model or knowledge of which samples are contaminated. UBD estimates a per-sample correction scalar from ensemble uncertainty, which is used to construct a debiased target distribution that suppresses the inflated probability mass on correct answers induced by contamination. This target is then used either as a post-hoc output correction (debiasing) or as a soft training signal for parameter update (unlearning). Experiments on MMLU-Pro and MATH-MCQA across multiple LLM backbones demonstrate that UBD produces per-sample output distributions substantially closer to those of an uncontaminated model than paraphrasing or choice-permutation baselines, while preserving model performance on uncontaminated data.

Scientists do not, by profession, wage war. Yet warfare's vocabulary consistently appears in their abstracts. To quantify the extent to which warfare's vocabulary pervades scientific abstracts, we analyze 21.4 million papers (2010-2025; OpenAlex, PubMed). We additionally run a within-subject war-framing experiment (N = 801; 32,040 trials) designed to provide causal insight into the effects of militaristic language on persuasion. Between 2010 and 2025, the presence of militaristic terms in scientific abstracts rose 48% in OpenAlex and 32% in PubMed, with the rise accelerating sharply after 2019 (cross-database r = 0.96, p < 10^-8). The prevalence of militaristic language is conflict-aligned at both country and annual scales (Uppsala Conflict Data Program; r = 0.77-0.84), with the abstracts from the Global South displaying the fastest rise in militaristic language. Among disciplines, social sciences leads in level of such language while engineering and computer science lead in growth. The COVID and post-2022 large-language-model eras also saw the rise and narrowed the language gap between native-English and non-English authors. In our follow-up experiment, we found that war framing reduced credibility (mean shift -0.18 Likert units, 95% CI [-0.21, -0.14]; d_z = -0.28, p < 10^-20), funding willingness (d_z = -0.12) and policy support (d_z = -0.08), with a trend-level increase in sense of urgency (d_z = +0.07). Collectively, findings reveal that while scientific abstracts drift toward warfare, the use of militaristic language may erode credibility, funding willingness, and policy support.

Advances in generative AI have made image falsification highly realistic, demanding trustworthy authentication systems. Existing forensic detectors can target certain forgery types but lack interpretability, while vision-language models (VLMs) provide explanations but cannot exploit forensic traces for reliable detection. We propose Forensic Knowledge Graphs (FKGs), a unified framework that integrates forensic evidence extraction, structured reasoning, and human-interpretable explanation. Our FKG structure encodes forensic traces along with their causal dependencies and links to scene content. To generate accurate FKGs, we introduce a novel forensic authentication network and an Iterative Context Refinement strategy that guides VLMs to produce faithful, grounded explanations. We also present FKG-50K, a dataset of 50,000 realistic forgeries with ground-truth FKGs. Experiments demonstrate that FKG outperforms both forensic detectors and VLMs in detection, forgery identification and localization, and forensic justification.

In sparse Mixture-of-Experts language models, does the same token id imply the same router state and the same experts producing it? Holding the emitted token id fixed at repeated anchors, we find it does not: the experts that produce it still separate task context, trajectory history, and reasoning-effort mode. This residual structure supports test-time control: near boundary anchors (the final-response transition) and delimiter anchors (which open the answer, e.g.\ \texttt{\textbackslash boxed\{} or code fences), routing neighborhoods already align with final-answer basins at a marker-only readout and strongest when the routing is read at the answer opening. We operationalize this as RAD (Routing Agreement Decoding), an answer-string-free multi-rollout selector: it locates a fixed anchor, represents each rollout by its anchor-window MoE routing states, and returns the densest Weighted-Jaccard $K$-NN route-basin center, without parsing, normalizing, executing, or voting over answer strings. Across 10 sparse-MoE configurations (gpt-oss, Qwen3-MoE) and 6 datasets spanning math, GPQA, and code, RAD is on par with Majority where string voting is well-posed, with small positive paired deltas (RAD $73.9$ / RAD+DC $74.2$ vs.\ Majority $73.6$). Like majority voting, RAD is not a verifier: a dense wrong basin can still win. Its value is the interface: the same selector gives direct pass@1 on code, where exact-string voting is ill-defined, and the same routing-density principle, re-anchored to the agentic boundary, improves best-of-16 patch selection on SWE-bench Verified over random, where patches have no answer string to vote on.

As Large Language Models (LLMs) achieve widespread integration across diverse linguistic landscapes, ensuring their safety and alignment with regional normative values remains a critical challenge. Current safety mechanisms are predominantly optimized for English-centric frameworks, often failing to capture the unique socio-cultural sensitivities and localized categories of harm inherent to the Indic region. To address this gap, we introduce IndicGuard, a multilingual safety guard model and dataset for Indic languages. We construct a high-volume, culturally nuanced safety dataset encompassing ten major Indic languages, systematically curated to capture regional harms, sensitive socio-political contexts, and adversarial jailbreaks. Leveraging this corpus, we fine-tune a 4B-parameter instruction-tuned model based on Gemma-3-4B-IT to serve as a multilingual safety guardrail for real-time content moderation and policy compliance checking. Our empirical evaluations demonstrate that IndicGuard significantly enhances LLM robustness against localized vulnerabilities, achieving high moderation consistency across different conversational turns. Crucially, IndicGuard consistently outperforms the existing baseline model, CultureGuard, across evaluated languages. Finally, we demonstrate that our model effectively generalizes to low-resource Indic languages excluded from training, substantiating the structural robustness and cross-lingual transfer capabilities of the framework.

Multi-arm manipulation demands precise spatiotemporal coordination, yet many centralized approaches scale poorly as team size increases. To address this, we propose CLS-DP, a decentralized multi-agent framework that enables implicit coordination under partial observability without shared global views, explicit state information, or inter-agent communication. Under the centralized training and decentralized execution (CTDE) paradigm, CLS-DP distills privileged multi-agent dynamics into a latent space. At deployment, each agent infers a collaborative latent from its local RGB observation and a shared task instruction; it then conditions the diffusion denoising process on this latent. This design enables implicit coordination with a per-agent cost independent of team size. Across six RoboFactory benchmark tasks spanning two to four agents, CLS-DP achieves a 38% mean success rate, outperforming the best centralized baseline (20%) and a decentralized ablation without the collaborative latent (9%). It also maintains superior parameter efficiency across all agent configurations. Attribution maps show that an agent conditioned on the collaborative latent places high attribution on the joints and grippers of both itself and its teammates throughout execution. This suggests that the learned latent efficiently encodes collaborative dynamics from local observation, which facilitates implicit coordination in realistic settings characterized by partial observability.

Evolutionary agent-based markets (ABMs) couple several mechanisms — who reproduces, how price forms, how biased the agents are, how consensus propagates — yet these are usually fixed by convention, so it is unclear which mechanism controls which emergent property. In a coevolving, endogenous-price simulator with 120 heterogeneous behavioral agents, we make four mechanisms pluggable and run matched 3x20-seed interventions. We find the levers are largely separable. (1) Selection -> diversity: a Quality-Diversity (QD/MAP-Elites) operator robustly raises strategy-mix entropy over truncation top-k (paired Delta entropy +0.27 to +1.12 bits; sign-test p<0.001; CIs exclude 0) and sustains more strategy cycling (strongest in crisis: Delta=+0.070, p=0.0004). (2) Selection does not improve realism: even a per-agent realism reward that provably steers selection does not raise 5-fact realism (Delta_5=-0.11,-0.08,+0.03; not significant). (3) Microstructure -> realism: enabling reflexive price feedback does raise realism (Delta_5=+0.13,+0.20,+0.20; crisis/bull p<0.05, all CIs positive). (4) Behavior -> fragility: amplifying behavioral bias raises a genomic fragility proxy (Delta=+10.5,+11.1,+14.4; bull p<0.001, all CIs positive) while leaving realism flat. The remaining mechanism — consensus network topology — shows no robust effect (honest null). The contribution is a decomposition: in these single-mechanism sweeps the mechanisms behave as approximately distinct control knobs over diversity, realism, and fragility.

Intrinsic self-correction (SC) aims to improve large language model outputs by prompting a model to revisit its own initial answer without external feedback. Recent studies have questioned the reliability of this approach, showing that models often struggle to judge whether their initial responses are correct. In this work, we take a task-sensitive view of SC. Rather than asking whether it works in general, we examine settings where SC may operate through different mechanisms: verifying explicit constraints, revisiting a complex reasoning process, or providing a second opinion over competing strategies in word-game tasks. Across multiple benchmarks and models, we find that SC can yield consistent performance gains when the underlying task structure facilitates these modes of revision. These results suggest that SC is best understood as a task-dependent inference-time strategy whose usefulness depends on the role the revision stage can play in a given task, rather than as a uniformly reliable method for improving initial model outputs.

Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed multi-layer world model capturing the complex relations of its surroundings. Hierarchical 3D scene graphs address this challenge by integrating geometric, semantic, and relational data within a unified spatial framework. However, current 3D scene graph approaches often restrict themselves to rigid structures of pre-determined relationship classes, mostly neglecting important semantic connections, like causal connections or environmental contexts. This paper explores the potential of foundation models to build forests of 3D scene graphs with open semantic relationships to improve scene understanding and robotic task execution. We propose a method where instance-specific concept-nodes and relationships are first identified by a VLM and extended upon by a LLM, inferring broader, more abstract concept-nodes and relationships through reasoning. These object-nodes, concept-nodes, and relationships are then assembled into a forest of hierarchical 3D scene graphs, enhanced with concept-nodes to represent abstract concepts. Evaluations were conducted on the uHumans2 and ScanNet indoor dataset, validating the accuracy and relevance of the generated relationships. Downstream suitability of scene-graph forests for robotics applications is demonstrated in an open-vocabulary object-retrieval task utilizing both ScanNet data and a real-world indoor deployment using a Boston Dynamics Spot. This paper leverages foundation models to create more expressive, semantically deep 3D hierarchical scene graphs and demonstrates their potential to advance semantic and environmental understanding in robotics.

Recent large language models (LLMs) are good at general text generation, but it is still hard to use them for domain-specific data generation because the output must follow strict formatting and structural rules. Unlike open-ended tasks such as question answering or translation, domain-specific generation must be both semantically correct and compliant with existing guidelines and standards. In this work, we study the nationwide interoperability problem of utility power outage reports in the United States. In practice, outage reports need to be machine-readable (e.g., JSON or XML) and must strictly follow requirements from energy-sector regulatory bodies. To address this problem, we propose POTracker, an optimized LLM for power outage report generation. We fine-tune Qwen2.5-7B-Instruct using our proposed objective. The key contribution is a new loss function, POTrackerLoss, that considers both textual similarity and structural (tag) similarity between the generated report and the ground-truth report. We evaluate POTracker on a dataset of 1,000 power outage reports and compare it with five well-known fine-tuning methods and one rule-based XML conversion method. Results show that POTracker outperforms other fine-tuning approaches, improving overall accuracy by up to 51% and reaching 86.47% structural accuracy for generated power outage reports. In addition, we conduct a human study to assess the quality of the ground-truth standard reports, where domain experts assign the generated labels an average score of 4.03 on a 0--5 scale.