Knowledge
-
Mechanistic Interpretability Needs a Logic of Inference
2026-11-10 18:45:07Zhimin Hu, Chen Jiang, Hanbo Xie, N. Apurva Ratan Murty, Sashank VarmaAbstract
Neural networks are increasingly studied not merely as predictive systems, but as complex systems whose internal computations are themselves objects of scientific inquiry. Recent progress in mechanistic interpretability (MI) has made it possible to identify neurons, features, circuits, population structures, and dynamical patterns associated with model behavior. As these tools improve, attention is shifting from what can be observed inside a model to how those observations support mechanistic explanations. We examine the parallel efforts of neuroscience and MI to address this question and identify recurring inferential bottlenecks when inferring mechanisms from complex neural systems. We propose five principles and organize them into a recursive logic for a more rigorous procedure of mechanistic inference. These principles provide a framework that supports scientific discovery in two senses: it helps turn local interpretability findings into cumulative knowledge of mechanisms within models, and it makes those mechanisms sufficiently precise to generate testable hypotheses about domains beyond the models. Evidence beyond MI is ultimately required to establish what model mechanisms reveal about the world.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14483
PDF
-
BoviShift: A Six-Year Multi-Attribute Audit of Visual Cattle Phenotyping Across Animals and Time
2026-11-10 18:38:23Mobasshir Bhuiya Shagor, Nilambar Halder Tonmoy, Md Saef Ullah MiahAbstract
Computer vision offers a scalable, non-contact means of estimating livestock traits, but correlated images and video frames make reliable evaluation difficult. Image-random splitting can place views of the same animal in both training and test sets, while deployment further requires transfer to animals captured in future years. We introduce BoviShift, a corpus reconstructed from six consecutive annual cohorts of an operational cattle marketplace collected from 2021 to 2026. It contains 2{,}657 cattle, 10{,}610 still images, and 2{,}566 walk-around videos across nine recorded breed categories. We evaluate three splitting strategies through four configurations: image-random and pooled cattle-disjoint splits over the same development cohorts, followed by separate future-2025 and locked future-2026 evaluations. Using a fixed ResNet-50 multi-task baseline, we assess weight, age, height, breed, and coat color. Differences between image-random and cattle-disjoint splitting are task-dependent rather than a universal leakage penalty. Future-cohort behavior is also attribute- and cohort-specific: breed declines relative to pooled evaluation; mean weight and age performance fails to beat constant baselines in 2025; height remains above baseline; and color transfers well to 2025 but degrades in 2026. Multi-task training improves all five point estimates in a single-seed ablation, still-view aggregation helps selectively, and zero-shot video-frame aggregation exposes a still-to-video domain gap. To our knowledge, BoviShift is the longest-spanning cattle-vision resource combining consecutive annual cohorts with physical and visual attributes.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14476
PDF
-
Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications
2026-11-10 18:01:23Sourish Gunesh Dhekane, Abinaya Kumar, Torsten Woertwein, Yan-Bo Lin, Thomas Ploetz, Shabnam GhaffarzadeganAbstract
Time-Series Foundation Models (TSFMs) are increasingly used in sensor applications, where sampling frequency (SF) varies across sensors, devices, and operating modes (e.g., power saving). Ideally, TSFMs must remain effective during such SF changes, provided the SF retains task-critical bandwidth. In this paper, we stress-test 4 prominent TSFMs: MOMENT, Chronos-2, Moirai-MoE, and TimesFM, to quantify their SF-invariance and investigate whether their behavior tracks the resulting loss of information bandwidth rather than the SF value itself. Our stress-test probes 3 dimensions: (i) the shift in embeddings, (ii) the degradation in forecasting performance, and (iii) the degradation in downstream performance, quantified by three novel metrics: FSI, FDI, and CDI, respectively. To our knowledge, this is the first study to place SF-invariance at the core of TSFM evaluations. Our results characterize: (i) how SF-invariance depends on the margin between signal's native-SF and the bandwidth its task requires, (ii) how much of that invariance the choice of TSFM explains, and (iii) how much of TSFM's performance degradation under a lower SF reflects information loss rather than a limitation of their abilities. These findings reframe SF-invariance as a measurable, signal-aware property of the (signal X TSFM) pair, and guide practitioners on when TSFMs display SF-invariance.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14425
PDF
-
EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities
2026-11-10 17:16:47Zhengxiang Huang, Yujie Sun, Shengheng Chen, Zhaode Wang, Chaoyue Niu, Zeyu Zhao, Chengfei Lv, Fan Wu, Guihai ChenAbstract
Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often miss these cross-layer dependencies and struggle to diagnose failures across host--device execution paths. We present EngineAgent, an agentic system for automating on-device LLM model enablement. Its key insight is to separate reusable engine and hardware knowledge from model-specific implementation. Before enablement, EngineAgent constructs a hierarchy-aware engine index that captures engine abstraction layers and cross-layer dependencies, and pre-validates backend-specific build, execution, and debugging workflows using already supported models. For each new model, a builder uses this knowledge to coordinate cross-layer changes, while an auditor checks implementation completeness and drives iterative debugging through device-side validation. Across 12 tasks spanning three mobile LLMs and four engine--backend pairs on CPUs, GPUs, and NPUs, EngineAgent achieves 75% end-to-end success with either of two underlying LLMs, versus 33.3% for the strongest coding-agent baseline. Success requires compilation, on-device execution, and output-logit agreement with reference implementations. EngineAgent also reduces average per-task time and model-API cost relative to baselines using the same underlying LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14356
PDF
-
When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
2026-11-10 16:52:25Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao, Zihao Zheng, Zecheng Sheng, Liwei HouAbstract
LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived behavioral update should be admitted into persistent agent state. We propose Falsification-Gated Self-Evolution (FGSE), a verifier-grounded framework that represents each candidate lesson as a structured hypothesis with an explicit precondition, behavior change, expected effect, and verifier. FGSE applies the hypothesis only in a temporary state, tests it on target-transfer, falsification, and archived-regression probes, and then commits, refines, or rejects it according to measured gain and risk. Across web, app, tool-use, and long-term memory benchmarks, FGSE achieves strong task performance, including 39.8 WebArena success rate, 78.8 AppWorld average completion, and 0.724/0.487 Pass$^1$ on $\tau$-Retail/$\tau$-Airline, while reducing falsification failures to 5.0%, regression damage to 1.3%, and harmful committed updates to 3.6%. These results suggest that testing memory updates as hypotheses supports more reliable long-term adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14326
PDF
-
MMDM: Measuring Massive Multitask Decision Making
2026-11-10 16:40:50Junhao Shen, Qing Zong, Yue Guo, Zhanqiu Zhang, Yiwen Guo, Hong ChengAbstract
System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior exposure to test material can obscure generalization. Moreover, real-world decision making often involves long contexts, large option spaces, and complex logical dependencies, challenges that existing benchmarks do not adequately capture together. Thus, we introduce MMDM (Massive Multitask Decision Making), a benchmark of 5,448 high-quality questions across 16 task categories, combining newly constructed tasks with source-grounded recompositions and rewrites for single-select, multi-select, and soft-label decision making in fresh contexts. It covers realistic scenarios such as agent state tracking, tool and skill selection, preference judgments, and rubric scoring, with option spaces ranging from 2 to 1,024 and inputs extending to 64,817 tokens. With MMDM, we conduct a comprehensive quantitative evaluation of 28 decision models, showing that many perform well on common knowledge yet struggle with interdependent options, constrained decisions, and multi-select tasks. For example, Perplexity Decider-V1.2 reaches 78.75% Hard Single-select Accuracy on world knowledge, but only 53.95% on option logic and 47.95% on constraint planning, while the best Hard Multi-select Accuracy across all models is 36.81%. These results highlight joint reasoning, constraint-aware selection, and complete multi-select recovery as key priorities for decision model development, with MMDM providing a testbed for measuring this progress.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14309
PDF
-
Representational Atoms in Neural Networks
2026-11-10 14:56:23Chenhui Hu, Pengfei Cao, Kang Liu, Jun ZhaoAbstract
Understanding the internal representations of neural networks and characterizing their relationship with human conceptual structure are two critical questions for elucidating model mechanisms. The former reveals how learned knowledge is organized in internal representations, whereas the latter provides a basis for interpreting these representations through human conceptual structure. Here, we formally define fundamental representational units (FRUs) and establish two evaluation criteria: fidelity and stability. We further prove that threshold-activated sparse autoencoders (TSAEs) can identify FRUs with high fidelity and stability under appropriate conditions, and validate this result through large-scale experiments. Further analyses reveal that FRUs with higher stability exhibit greater monosemanticity and can be composed across layers to recover semantic organization corresponding to human conceptual structure. These results provide a unified framework for defining, evaluating and identifying FRUs in neural networks, and establish a foundation for characterizing the relationship between neural network representations and human conceptual structure.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14168
PDF
-
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
2026-11-10 13:47:29Tomer SolbergAbstract
We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.14083
PDF
-
Program-Aided Patchable Skill Evolution
2026-11-10 12:53:12Jiahao Wang, Yuqi Xiong, Qing Yang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yubin BaoAbstract
Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based on downstream task feedback. However, existing methods primarily represent skills as natural language documents, intertwining procedural logic with descriptive knowledge and making skills difficult to maintain and evolve. To address this limitation, we propose PASE (Program-Aided Patchable Skill Evolution), a program-aided framework that iteratively evolves skills by associating them with executable programs. Unlike prior approaches that encode trajectory-derived experience primarily in natural language, PASE separates reusable procedural logic into editable programs, enabling targeted updates to executable components while reducing the need to repeatedly revise natural language skills. Extensive experiments across diverse models and benchmarks demonstrate that PASE consistently outperforms all baselines, by achieving over 2.8% improvements. Further analyses show that PASE exhibits greater evolutionary stability and generalisation capability, highlighting the critical role of programmatic knowledge in skill evolution. We will release all data and code via GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14019
PDF
-
Spatio-Temporal Calibration of a Vehicle-Mounted Microphone Array for Autonomous Driving
2026-11-10 12:44:52Marvin Seegert, Richard Taupitz, Korbinian Moller, Johannes BetzAbstract
Microphones let an autonomous vehicle sense into areas its cameras and LiDAR cannot see, by picking up the sound that other traffic participants emit. Locating those sources and fusing them with the visual perception requires the microphone array to be calibrated and registered relative to the vehicle's other sensors. Existing calibration methods assume small, unobstructed indoor rigs, whereas a vehicle body casts an acoustic shadow that straight-line propagation cannot represent, and to our knowledge no calibration of an array distributed around a vehicle has been reported. We propose a pipeline that uses a balloon burst as a single cross-modal target, which the LiDAR locates in metric coordinates, every microphone hears as a sharp onset and a camera times. Each observation is weighted by its own timing variance, which discounts shadowed arrivals instead of discarding them and needs no model of the vehicle. On a full-size vehicle with eight microphones over a 4.9 m aperture, the held-out range residual of 6.37 cm approaches the 6.07 cm floor set by the onset timing noise, and the calibrated array tracks a moving source to within a few degrees of the vehicle's own LiDAR. A dozen bursts spread around the vehicle suffice, and spreading them matters more than adding more.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14003
PDF
-
Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies
2026-11-10 12:04:54Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert StahlbockAbstract
Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13966
PDF
-
Tailoring Optimization Approaches with Domain Knowledge in Industry Process for Meta-heuristic Development
2026-11-10 11:24:26Jakub Cebula, Konrad Gmyrek, Pawe{\l} B. Myszkowski, Marko {\DJ}urasevi\'c, {\L}ukasz P. Olech, Adam Paliszek-Sa{\l}adygaAbstract
The paper presents an Industry Process for Meta-heuristic Development (IPMD) schema, a systematic methodology for applying meta- and hyper-heuristic applications to optimization problems. In this context, we present a case study of Balancing Non-dominated Tournament Genetic Programming (BNTGP) applied to solve two NP-hard multi-objective optimization problems: routing (Capacitated Vehicle Routing Problem with Time Windows) and scheduling (Multi-Skill Resource Constrained Project Scheduling Problem). The BNTGP method is based on a metaheuristic design. Its genetic programming-based representation makes BNTGP a hyper-heuristic, as it enables the exploration of a search space of heuristics for solving problems in general. The resulting heuristic can then be applied across a set of problem instances.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13940
PDF
-
MEOW: Medical Open-World Interactive Segmentation
2026-11-10 11:21:59Philip Matthias Winter, Maria Wimmer, Bernhard Sch\"{a}fl, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Ariharasudhan Muthusami, Johannes Novotny, Georg Zotti, Katja B\"{u}hlerAbstract
In open-world recognition, machine learning models not only make predictions on unknown structures ("generalized open-set"), but also continually learn and improve from those predictions over time. Interactive segmentation, despite its access to user feedback, has so far remained confined to the open-set setting. In this work we introduce MEOW, the first framework that turns non-interactive segmentation backbones into interactive open-world learners without updating learnable model parameters. MEOW combines parameter-free transductive reasoning with memory consolidation to accumulate knowledge and thereby improve future performance. Focusing on medical data, we show that MEOW consistently improves its own predictions on classes never seen during training, and transfers zero-shot to unfamiliar domains, including micro-CT data and other imaging modalities.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13935
PDF
-
Learn-To-Propagate: Distributionally Robust Motion Planning for Nonlinear Uncertain Systems
2026-11-10 10:23:12Eduardo Figueiredo, Adrien Banse, Qi Heng Ho, Raphael Jungers, Morteza Lahijanian, Luca LaurentiAbstract
Motion planning for stochastic systems aims to find a sequence of control inputs that drives a system to a goal set while avoiding unsafe states with high probability. Existing approaches, however, are either restricted to linear dynamics with perfect knowledge of the underlying distributions or lack formal correctness guarantees. To address these limitations, we propose \emph{Learn-To-Propagate Distributionally-Robust Forest (L2P-DR-Forest)}, a distributionally-robust sampling-based planning algorithm for \emph{nonlinear} stochastic systems with \emph{unknown} initial state and process noise distributions. Our approach leverages recent advances in optimal transport to learn ambiguity sets that contain the true system distributions with high confidence. We develop an efficient method for propagating these sets through the system dynamics and for verifying their safety. We then integrate these techniques into a novel sampling-based planning algorithm to grow a forest of search trees in the system's state space while accounting for and mitigating the growth of ambiguity-sets radii. We prove that the algorithm is correct, i.e., every returned plan satisfies the specifications with the prescribed confidence, and, under some feasibility and distributional assumptions, is probabilistically complete. Evaluations on several robotic benchmarks demonstrate that our algorithm significantly outperforms existing methods while providing formal guarantees with high confidence.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13863
PDF
-
Beyond Passive Imitation: On-Policy Mid-Training Distillation for Language Models
2026-11-10 10:15:20Ruize Zheng, Xuyang Liu, Siyu Ren, Xiaobing Tu, Yinggui Wang, Jinkui Ren, Xiantao Zhang, Linfeng ZhangAbstract
Continual pre-training (CPT) adapts large language models (LLMs) to specialized domains, yet its standard next-token prediction (NTP) objective treats every corpus token as a fixed target, regardless of its utility to the current model. In a controlled study on the same 1B-token mathematical corpus, we observe sharply different outcomes across base models: NTP improves Llama-3.2-3B's performance on mathematical benchmarks but substantially degrades Qwen3-1.7B-Base's performance, indicating that, under a fixed training recipe, the same training sequences can have model-dependent effects. To address this problem, we introduce On-Policy Mid-Training Distillation (OPMD), which reformulates mid-training from offline text imitation into active, query-driven knowledge acquisition. At selected anchor positions, OPMD samples trajectories from the evolving student policy and applies dense token-level reverse-KL rewards from a frozen teacher, training the model on states it actually visits rather than only on ground-truth prefixes. This on-policy objective reduces the training-generation mismatch of teacher-forced NTP. On MATH-500 and Minerva, OPMD improves the Qwen student over its base performance and outperforms the evaluated NTP baseline, which degrades on both benchmarks. OPMD integrates into CPT pipelines without added inference-time overhead and offers a model-aware alternative to passive domain adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13855
PDF
-
STABLE: A Continual Learning Optimizer with Adaptive Drift Control
2026-11-10 10:00:14Xiaoyan Li, Lanpei Li, Massimo Coppola, Vincenzo Lomonaco, Antonio CartaAbstract
Continual learning suffers from catastrophic forgetting, leading to the loss of past knowledge and unstable adaptation across task streams. Existing approaches typically address this issue through replay buffers, architectural changes, or additional regularization terms. We argue that forgetting is a consequence of unstable learning dynamics, which may benefit from an optimizer-level solution. The main challenge is that learning dynamics are time-dependent, as demonstrated by empirical phenomena such as the stability gap. First, we formally prove that, for distance-based classifiers, bounded parameter drift guarantees bounded margin erosion under a local score-stability condition. Based on this insight, we propose STABLE, a primal-dual optimizer with adaptive drift control. STABLE enforces a drift budget by increasing the dual variable when the budget is violated and decreasing it otherwise. This results in high stability without penalizing plasticity. Experiments on long-horizon unimodal streams and CLIP-based multimodal streams show that vanilla PEFT baselines trained with STABLE match or outperform specialized continual learning methods. In the multimodal setting, STABLE further preserves zero-shot transfer, matching or exceeding dedicated multimodal continual learning methods. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10655
PDF
-
Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation
2026-11-10 09:57:01Luca Favole, Giorgio Mongardi, Giovanni Squillero, Alberto TondaAbstract
The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to assess the capability of Artificial Intelligence (AI) systems to generalize starting from a few samples, a task humans excel at. The ARC-AGI contests held since 2020 have been the focus of intense competition, with participants proposing approaches ranging from traditional symbolic AI to Transformer architectures. Despite a long history of successes, evolutionary algorithms (EAs) were notably absent from the approaches appearing in the main contest. As score-and-search program synthesis approaches, EAs suffer from issues related to choosing the proper representation in the Domain-Specific Language applied to the problem (for example, pixel-level or object-level), and distinguishing between two candidate solutions producing the same outputs. In this work, we present the first fully symbolic, evolutionary-based program synthesis approach submitted to the ARC-AGI-2 main contest. The main contributions are: evolving the grid parser and the output projector together with the program that transforms the grid, so that a task-specific language emerges during program synthesis; grounding the symbols the parser can extract in core knowledge theory from cognitive psychology; and an object-aware fitness that grades partially correct outputs beyond pixel-level discrepancies.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13831
PDF
-
CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation
2026-11-10 08:35:27Choo Sin Wai, Dake Zhong, Jingye Zhang, Zhifang Liu, Siyao Xiao, Zirong Ding, Yuhong Zhang, Kangjie Chen, Dongbin Zhang, Guorui Song, Guocun Wang, Peng Jiao, Haoqian WangAbstract
Robot demonstrations contain reusable manipulation knowledge, but transferring this knowledge across embodiments requires representations that bridge differences in control interfaces. Action reconstruction alone does not ensure that similar behaviors across robots share a representation. To address this gap, we introduce CIALLO, an action codec that aligns actions, visual changes, and observation-grounded language in a shared space of short-horizon behavioral intent. An embodiment-conditioned decoder maps this intent back to robot-specific actions, allowing a shared representation to support different control interfaces. After pretraining on eight embodiments, CIALLO adapts to a new robot from one recording of at most 10 seconds by updating only its embodiment embeddings. The calibrated codec then remains frozen while a policy learns to predict intent from observations and instructions. We instantiate this policy with Qwen3.5-4B to form Qwen-CIALLO, whose backbone requires no large-scale robot-action pretraining before policy finetuning. With 20 demonstrations per task, Qwen-CIALLO achieves 76.7\% average success across real SO-101 and single-arm Piper robots, compared with 70.0\% for fully finetuned $\pi_0$. In simulation, we additionally finetune the action decoder, achieving 97.3\% success on LIBERO and 52.7\% on RoboTwin 2.0. The LIBERO policy also achieves 80.8\% on LIBERO-Plus without further finetuning. Together, these results support a shared action codec as a transferable control interface that separates embodiment calibration from task learning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13732
PDF
-
FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge
2026-11-10 08:18:50Siyuan Li, Ke Wan, Boyong Hou, Yujie Deng, Zixuan YuanAbstract
In financial backtesting and other point-in-time tasks, external inputs can be restricted by date, but model parameters may retain financial facts disclosed later, introducing parametric look-ahead bias. We introduce FinCutBench, a continually updated monthly financial knowledge benchmark for measuring how far a fixed model's financial knowledge extends over calendar time. The current dataset contains 9,000 Chinese and English four-option multiple-choice questions from January 2023 to September 2026, covering Chinese and U.S. markets and four categories of financial information. We construct monthly knowledge profiles using the approximate months in which the tested facts became public. After a profile passes the decline test and knot checks, we define the FinCut Boundary as the first month when the fitted profile reaches its lower level, and report the stability of the estimated date under resampling. Boundary dates and localization precision vary across models. Using the independently measured Transition Start and Boundary as fixed references for downstream sample grouping, we find significant relative declines in U.S. asset-ranking performance and in earnings recall for Sol and Luna. Downstream effects vary across markets and tasks. The FinCut Boundary thus provides an empirical reference for the temporal scope of parametric knowledge in point-in-time financial evaluation, supporting evaluation-window selection and result interpretation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11588
PDF
-
On Private Knowledge Retrieval and Private Inference for secure multi-agent systems
2026-11-10 07:43:02Vicen\c{c} Torra, Maria Bras-Amor\'osAbstract
Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an autonomous way. Agentic AI is the new term to denote these AI-based autonomous systems. In real multi-agent systems, agents need to deal with malicious agents some of which can exploit security vulnerabilities to do harm. A memory poisoning attack is an example of exploiting a vulnerability to modify agents knowledge and, thus, affect its behavior. In an agent, there are different types of memory systems (semantic, episodic, and short-term) which have their own characteristics and for which different memory poisoning attacks may be developed. In this paper we focus on semantic memory, we discuss its attack, and mitigation strategies. We introduce private knowledge retrieval and private inference. We propose a signature system in the knowledge base to prevent from undesired manipulation. This should avoid memory poisoning attacks by introducing security by design in the construction of the semantic memory. In our architecture, an agent contains a local Prolog-like inference system (i.e., using Horn clauses to represent knowledge) which accesses an external knowledge base to get the required knowledge. This externally signed knowledge base is accessed privately. We provide different implementations in Python using different privacy levels including k-anonymity and information-theoretical privacy (IT-PIR).
Abstract (translated)
URL
https://arxiv.org/abs/2611.13696
PDF
