Computation and Language
Generative Skill Composition for LLM Agents
Xinyu Zhao, Zhen Tan, Vaishnav Tadiparthi et al. (+5 more)
Recent LLM
agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for performing specialized tasks, such as setting up a sandboxed environment, running a test suite, or refactoring a function across multiple files. As skill libraries grow and become reusable across tasks and domains, selecting an appropriate skill composition has emerged as a central bottleneck. Existing approaches fall into two categories. One exposes the
agent's
reasoning to the entire skill collection; the other performs skill
retrieval via
embeddings or LLM-based rerankers. Both provide useful insights; however, they miss the structural nature of skill composition, which is a joint decision over which skills, how many, and in what order – three dimensions that cannot be decoupled. We formalize this as structured skill composition: given a task and a skill library, predict an executable skill plan that jointly specifies the activated subset, count, and execution order. We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction. SkillComposer uses a constrained autoregressive decoder over skill identifiers, so subset, count, and order emerge jointly from a single decoding pass, and dependencies between successive skills are captured naturally. We build a training set of task-composition pairs from a real, human-curated skill library. We then evaluate SkillComposer along two axes: composition quality on a held-out test set, and downstream task success on SkillsBench across two production-grade coding
agents. On GPT-5.2-Codex, Gemini-3-Pro-Preview, SkillComposer raises the pass rate by +23.1, +18.2pp over the no-skill baseline, surpassing top-3
retrieval and matching the gold-skill
retrieval upper bound at lower
prompt-
token cost.
Read the full abstract ▾
All authors Xinyu Zhao, Zhen Tan, Vaishnav Tadiparthi, Nakul Agarwal, Kwonjoon Lee, Ehsan Moradi Pari, Hossein Nourkhiz Mahjoub, Tianlong Chen
Computation and Language · Cross-listed from cs.LG
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
Jian Gu, Aldeida Aleti, Chunyang Chen et al. (+1 more)
Residual-stream analysis asks how
language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If
embedding anchors and unembedding readout disagree on the chosen span, apparent motion may reflect measurement drift rather than computation. We introduce Semantic Reference Frames (SemRF), an anchor-based formalism separating semantic measurement from residual dynamics. A SemRF fixes anchors and measures states against them. Pseudo-inverse tying gives exact synchronization; under restricted bi-invertibility, SemRF yields stable semantic-basis coordinates, distortion bounds, and near-identity changes. With the frame fixed, residual computation becomes a depthwise semantic trajectory. The anchors induce a semantic Voronoi diagram: distance, or evidence such as logits, assigns each layer to a coarse
cell, while coordinates retain within-
cell motion and margins. We define layerwise steps, contribution profiles, and imbalance diagnostics, then use the Voronoi trace to define a margin-relaxed tube. The canonical trace is the minimum-action path inside this tube; when nonempty with positive quadratic weight, it is unique and obeys a discrete spline equation away from active constraints. Excess action controls step,
curvature, and profile mismatch. Low
curvature implies piecewise-linear compressibility and local knowledge density: lower trace complexity means fewer semantic
knots. Through the parameter-to-trajectory map, this gives a conditional link to parameter efficiency: among admissible settings fitting data, lower-action and lower-complexity traces use fewer semantic degrees of freedom. The guarantees require controlled interface error and small projection residual under explicit tube constraints.
Read the full abstract ▾
All authors Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
Computation and Language
Scalable Behaviour Cloning on Browser Using via Skill Distillation
Kaisen Yang, Zheng Jiang, Yuzhao Peng et al. (+11 more)
Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser
agents is decision-making under incomplete information rather than low-level operation, and that the priors
agents lack are already implicit in human interaction traces. We therefore study scalable behavior cloning for browser
agents via skill
distillation, converting user interaction trajectories into compact natural-
language skills that
agents can read, retrieve, reuse, and compose directly. We further organize the distilled skills into a skill graph so that growth proceeds through consolidation rather than unbounded accumulation. This suggests that the scalability of browser
agents may come less from manually designed tasks and more from the collective skills already expressed by internet users. Our project is available at: https://lab.einsia.ai/browserbc/.
Read the full abstract ▾
All authors Kaisen Yang, Zheng Jiang, Yuzhao Peng, Houde Qian, Boshi Zhang, Youjie Zheng, Shijin Hong, Qingle Liu, Ruoyu Han, Bohan Lyu, Bingxiang He, Eren Cai, Calvin Xiao, Qinhuai Na
Computation and Language
DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching
Meng Chen, Anya Ji, Tsung-Han Wu et al. (+4 more)
Agents are increasingly capable of automating software tasks, but can they teach humans how to use software themselves? We introduce DigitalCoach, a
multimodal dataset of 72 human expert-novice computer use coaching sessions consisting of 22,752 dialogue turns grounded in 28.1 hours of screen and input event recordings across five software applications. We use DigitalCoach to evaluate whether state-of-the-art models can teach humans how to use computers. Automated evaluation shows that models differ from humans in how they coach: models provide more direct instructions, but fewer explanations, error diagnoses, and knowledge-check questions. When we fix the coaching method, models produce utterances similar to human references yet poorly grounded in visual context. Interactive evaluation confirms that model coaches cause learners to passively follow instructions without deeper engagement and fall short in visual grounding. DigitalCoach lays a foundation for collaborative and proactive computer use coaching
agents. Data and code are available at https://project-digital-coach.vercel.app.
Read the full abstract ▾
All authors Meng Chen, Anya Ji, Tsung-Han Wu, Tobias Maringgele, David M. Chan, Alane Suhr, Amy Pavel
Computation and Language · Cross-listed from cs.MA
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
Qingyun Liu, Jiwen Zhang, Jingyi Hu et al. (+2 more)
Recent
multimodal large
language models (MLLMs) have strong potential as
embodied agents, but their ability to collaborate in visually grounded environments remains underexplored. To address this gap, we introduce MECoBench, a
multimodal embodied cooperation
benchmark with an evaluation platform spanning diverse real-world tasks, two cooperation structures, and three collaboration modes. Through extensive experiments across various MLLMs, we summarize three key findings: (i) Collaboration generally improves
embodied task completion, but its benefits depend on balancing collaborative gains against coordination complexity. (ii) Communication is essential to collaboration gains, while the best collaboration mode depends on team size and model capability. (iii) Moreover, collaboration improves robustness under noisy priors and exploration conditions. Generally, MECoBench provides a systematic testbed for understanding the mechanisms and limits of
multimodal embodied collaboration. Code and
dataset are available at https://github.com/q-i-n-g/MECoBench.
Read the full abstract ▾
All authors Qingyun Liu, Jiwen Zhang, Jingyi Hu, Siyuan Wang, Zhongyu Wei
Computation and Language · Cross-listed from cs.LG
Signed-Permutation Coordinate Transport for RMSNorm Transformers
John Sweeney
Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$
neuron sets, attribution lists, and merge
alignments. This is only well posed after fixing the model's residual-stream gauge, which we show is architecture-dependent: LayerNorm residual charts have permutation gauge $S_d$ (up to a global sign flip), while RMSNorm charts with generic per-channel gain have signed-permutation gauge $B_d = S_d \ltimes \{\pm 1\}^d$. Permutation-only
alignment is therefore
symmetry-incomplete for RMSNorm models. We introduce sign-marginalized Hungarian matching and prove a sharp failure mode: with decorrelated coordinates, raw signed-correlation matching has a structural permutation-accuracy ceiling at the positive-sign fraction of the true gauge, which sign-marginalization removes. We then make coordinate-preserving transport, not function-level merging, the primary object: composing saved-checkpoint local $B_d$ gauges along same-base fine-tuning trajectories recovers 91.1% of cross-run coordinates at 1500 steps versus 60.3% for endpoint matching, and the gain is not explained by merely routing through the base. The recovered gauge transfers tools that permutation-only
alignment breaks: TinyLlama SAE reconstruction has NMSE 0.004 under $B_d$ versus 1.08 under $S_d$; Qwen sentiment steering preserves 95.8% of its effect versus 17.2%; refusal steering reverses sign under $S_d$; coordinate-preserving merges behave the same way. The same covariance governs stateful training: signed transport of AdamW state preserves the resumed trajectory, while permutation-only state follows a different one from a functionally identical checkpoint. Finally, gauge-sweep audits show index-level interpretability claims are reproducible only relative to an explicit gauge.
Read the full abstract ▾
Computation and Language
LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish
Nina Hosseini-Kivanani and Sandipana Dowerah
State-of-the-art
speech datasets predominantly focus on widely spoken
languages, often overlooking low-resource
languages such as Luxembourgish, which remain underrepresented in
speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive
speech corpus for Luxembourgish with 4
emotion categories. LuxEmo is derived from
Radio Télévision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising,
language identification, LuxASR-based
segmentation, automatic
emotion prediction, lexical cues, and targeted human review. Additionally, we
benchmark five expressive TTS systems covering German-based cross-lingual transfer,
multilingual Luxembourgish support, Luxembourgish adaptation, and non-parametric prosody transfer. Performance is evaluated using both objective metrics and human evaluation.
Read the full abstract ▾
Computation and Language
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
Ben Slater, Matteo G. Mecattaf, Lucy G. Cheke et al. (+2 more)
Theory of Mind (ToM)
benchmarks for Large
Language Models (LLMs) typically rely on passive question-answering formats, but the deployment of LLMs in increasingly agentic and autonomous forms demands new evaluations. In this paper we evaluate an
agent's ability to induce specific belief states in other
agents by taking actions rather than using conversational persuasion, a capability we call Non-Conversational Planning ToM (NCP-ToM). NCP-ToM is likely to be essential for many
agent use-cases, including within user-assistant interactions and pedagogical contexts, but may also present manipulation or misinformation risks. Using a novel framework, NCP-ExploreToM, we subvert the conventional task structure by providing models with a set of belief state goals and requiring them to move objects or direct characters into rooms to achieve their goals. We evaluated six frontier models, including GPT-5, Gemini 2.5 Pro and the Claude 4 series, and a cohort of human participants, across 600 task instances. GPT-5 was successful on approximately 80% of tasks in the agentic setting, and was the only model to outperform human participants on our task, but was still less robust than humans across contexts. We additionally found that all models, like humans, performed better on tasks inducing true belief states than false belief states, which is a positive signal for
alignment efforts. These findings highlight emerging social-
reasoning capabilities in LLMs for non-conversational task completion and underscore the necessity of agentic evaluations for understanding the safety and
alignment of autonomous social
agents.
Read the full abstract ▾
All authors Ben Slater, Matteo G. Mecattaf, Lucy G. Cheke, John Burden, Winnie Street
Computation and Language · Cross-listed from cs.LG
Review Residuals: Update-Conditioned Residual Gating for Transformers
Kyle Kramer
Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W[RMSNorm(h_{l-1}), RMSNorm(u_l)]). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two findings. First, a depth-stability result: a convex (Highway-style) form of the gate reintroduces vanishing gradients and fails to train beyond ~20 layers, whereas the additive, identity-preserving form trains stably at all depths we tested. Second, an emergence-with-scale result: trained from scratch across five sizes (60M-1B parameters, multi-seed), Review Residuals show no advantage at small scale but at 590M significantly outperform both a parameter-matched Highway gate and a parameter-matched standard residual (p<0.05), with a larger advantage at 1B. The benefit grows with model size rather than shrinking.
Read the full abstract ▾
Computation and Language
Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors
Mark Oskin
A
transformer's feed-forward (FFN) sublayer materializes the distinctions
attention gathers, yet gives no account of what it computes. In a parameter-neutral replacement, each hidden unit is an explicit fuzzy set operation on sigmoid-bounded [0,1] memberships: intersection A*B and set-difference A*(1-B), the latter a bounded positive negation ("A but not B") that gated/bilinear units lack – a negation-capable FFN (NC-FFN). On N-bit parity they are the most parameter-efficient
reasoning basis at shallow depth; at scale (125M, OpenWebText) NC-FFN ties the GELU baseline's perplexity, every unit carrying explicit logical form. Two limits share one cause: two-operand logic localizes to layer 0 and erodes under training, and the one robust grammatical deficit concentrates in licensing and quantifiers, beyond within-
token operators. We resolve both with a small block of sequence quantifiers: a soft existential and a soft proportion, each with a per-unit learned forgetting rate from a sticky init. This recovers the deficit at epoch one (halving the wider epoch-two gap), modestly leads on LAMBADA, and makes the FFN legible: the structure now holds and migrates into depth; the decay un-learns its stickiness (median half-life ~1.5
tokens; zero latch units); and at the semantic layers the units read, without dictionary learning, as grammatical licensing detectors: each fires on a licensor (a comparative, a passive participle, a negative-polarity item) and carries its
memory forward to predict the licensed word (than, by, nor). This legibility is localized and free only up to a partition (a fully Boolean FFN diverges in training), but the result is a parameter-neutral,
language-model-quality
transformer with a readable, interpretable-by-construction grammatical mechanism – an account not just of what a feed-forward layer represents but how it licenses.
Read the full abstract ▾
Computation and Language
CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield
Dohyeon Kwon and Youngjin Park
Frontier
language capability is usually bought with frontier compute; CHERRY shows a different trade. It is a sovereign Korean model family built on one principle: supervise the
tokens that decide the answer, and let shared weights carry the rest. Under matched compute this exposes a sharp, reproducible dissociation—selected-
token supervision preserves held-out discrimination yet collapses free generation, and a full-sequence anchor recovers only part of the gap. The same signal drives a heal-after-merge recurrent-representational-yield loop that collapses 48 layers to 6 unique blocks at near-dense parity (227M at loss 2.934 vs a 566M dense model at 2.926) and composes them by MoEE fusion (2.789)—a recurrent-compression direction independently pursued by concurrent frontier looped-MoE work, which we project (not yet measure) to frontier scale. It also installs metacognition from two-
token supervision (200 held-out KO
prompts/type, kappa>0.82, +/-6.9pp): self-correction 12->47% and jailbreak 23->4% at 97.6% loss-retention on 1.2B, with a pre-registered 1B->13.7B ablation localising the operand-binding limit to capacity (1B lookup vs 13.7B H-PRESERVE); and it specializes a 1.8B model to reported human-expert level on CyberMetric (75.0% vs a 30-expert average 72.24%). The released 1.8B tokenizer is 9.2% more Korean-efficient than Gemma-4; the from-scratch 12B adds a sovereign Korean tokenizer (vocab 131,037). On the government-operated K-AI Korean-LLM leaderboard the released 1.8B leads the HLE(Ko) column (0.123 vs 0.077; overall 51/78). At the frontier we fine-tune and serve an adapted 122B model on one 120GB accelerator (83GB measured peak). Provenance differs by member and we state it exactly; the architecture and recipe are ours throughout, and every claim is bound to a released curated measurement.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks
Thuan Bui, Duong Do, Tung Vu et al. (+2 more)
Log parsing is a fundamental step in automated log analysis, transforming raw system logs into structured event templates for downstream tasks such as anomaly detection and system monitoring. Existing log parsing methods range from rule-based and clustering-based approaches to neural models that learn semantic representations from log messages. However, neural approaches typically rely on dense
matrix multiplications, which can result in high computational cost and energy consumption. This paper presents SpikeLogBERT, a spiking neural network framework for energy-efficient log parsing. The proposed model integrates a spiking
transformer architecture with knowledge
distillation from a BERT teacher model, enabling spike-driven computation while preserving semantic representation capability. By leveraging sparse spike activations and event-driven processing, the number of active operations during inference can be significantly reduced. As an initial
benchmark study, experiments on the HDFS
dataset demonstrate that SpikeLogBERT outperforms ANN-based neural log parsing models with a parsing accuracy of 0.99997, while reducing estimated theoretical energy consumption by up to 62.6% under standard 45nm CMOS assumptions.
Read the full abstract ▾
All authors Thuan Bui, Duong Do, Tung Vu, Duc-Tho Mai, Cong-Kha Pham
Computation and Language · Cross-listed from cs.LG
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
Ying Fan, Anej Svete and Kangwook Lee
Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps
token-by-
token. Latent CoT offers an alternative: it performs multi-step
reasoning in the model's hidden states, replacing decoded
tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth,
Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent
reasoning. We therefore ask whether looped
Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded
Transformer that processes K latent blocks in parallel for R iterations, with a cross-
entropy loss on each latent position's gold CoT-step
token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped
Transformers with parallel supervision on latents). LOTUS is, to our knowledge, the first latent-CoT method to bridge the gap to explicit CoT at the 3B scale, while cutting thought-phase latency by 2.5x-6.9x from compact math expressions to natural
language. Projecting LOTUS's post-loop latents through the base LM head recovers the gold
reasoning steps and even surfaces alternative valid intermediate steps, evidence that its latent space is interpretable and CoT-aligned. Ablations confirm that both the looped backbone and the parallel supervision on gold CoT
tokens are essential. Code is available at https://github.com/yingfan-bot/lotus.
Read the full abstract ▾
Computation and Language
Rafael Rivera Soto, Anna Wegmann and Cristina Aggazzotti
While semantic
embeddings are rigorously evaluated on the Massive Text
Embedding Benchmark, the evaluation of style
embeddings remains fragmented, with each work relying on their own set of tasks and
datasets. To bridge this gap, we introduce the Style Text
Embedding Benchmark, a comprehensive open-source
benchmark intended to standardize the evaluation of style
embeddings. STEB encompasses 96
datasets across 7
languages, spanning applications such as authorship verification, authorship
retrieval, AI-text detection, probing of linguistic features, and others. We find that semantic
embeddings consistently fail in stylistic tasks, and that there is no style
embedding that is universally superior across all tasks evaluated. We open-source the STEB code base at: https://github.com/rrivera1849/STEB.
Read the full abstract ▾
Computation and Language
Adapting Foundation ASR Models to Dysarthric Speech: A Case Study
Christian Huber, Laura Kernahan and Alexander Waibel
Automatic
speech recognition (ASR) systems often perform poorly in dysarthric
speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool, we collected 92 hours of read
speech and later added 8.8 hours of user corrections gathered through a deployed mobile application. Starting from Whisper, fine-tuning reduced word error rate to 15.8% with only 1.4 hours of adaptation data on the read test set, reached 10.7% / 16.1% with 22.5 hours on the read and corrections test sets, respectively, and achieved the best result of 9.7% when using all available data including the corrections on the read test set and 7.8% on the corrections test set. Using LoRA adaptation and/or Qwen3-ASR as foundation model performed worse in this setting. The results show that personalized fine-tuning can make foundation ASR models substantially more effective for dysarthric
speech and suitable for practical deployment.
Read the full abstract ▾
Computation and Language
Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue
Nan Li, Albert Gatt and Massimo Poesio
In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. We investigate whether
vision-
language models (VLMs) can distinguish what could be shared from what has been shared between dialogue participants through grounding. We formulate this as an interpretation-matching task on 13,077 annotated reference expressions from HCRC MapTask dialogues, and evaluate VLMs under systematically controlled manipulations of dialogue context and map-information access. Our results show that providing authentic map images improves overall performance but shifts models toward over-predicting
alignment. Textual descriptions of the same map content reproduce this bias, while non-informative images suppress
alignment predictions entirely, indicating that the bias is driven by task-relevant map content, not the visual channel. This improvement comes at the cost of degraded accuracy on non-aligned cases. Calibration analysis and reference-chain tracking further suggest that models rely on static referential cues on the maps rather than tracking how grounding unfolds through dialogue history. We observe these patterns most clearly in Qwen3-VL-8B-Instruct and, to varying degrees, in four additional models from two architecture families. In models that exhibit the bias, map content, whether presented visually or textually, is treated as evidence of mutual understanding, conflating potential with established common ground.
Read the full abstract ▾
Computation and Language
Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian
Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma et al. (+2 more)
Relation extraction (RE) for low-resource
languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross-lingual RE for Romanian by combining automatic
dataset translation with large
language model (LLM) inference. We translate the SemEval-2010 Task 8
benchmark from English to Romanian using an LLM-based translation pipeline and evaluate Gemma 4 31B under zero-shot, few-shot, and QLoRA fine-tuned configurations, against four encoder baselines spanning 125M to 560M parameters: XLM- RoBERTa (base and large), Romanian BERT, and RoBERT- large. We assess two task formulations: relation classification with marked entities and end-to-end extraction. Our results show that Romanian incurs a 3 to 5 percentage point (pp) drop relative to English in
prompt-only settings, that few-shot prompting provides marginal gains over zero-shot, and that QLoRA fine-tuning improves macro F1-Score by more than 22 percentage points in both
languages while reducing the cross-lingual gap from 3.3 to 1.4pp. The encoder baselines come within 1-4pp of QLoRA Gemma on Romanian despite being 50-250 times smaller, with monolingual Romanian BERT at 125M parameters matching
multilingual XLM-R at 278M. The case for using a 31B model for single-task RE on Romanian is therefore weak in deployment scenarios where compute matters. We release the translated
dataset, evaluation code, and trained models.
Read the full abstract ▾
All authors Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma, Adrian Paschke, Ciprian-Octavian Truica
Computation and Language · Cross-listed from cs.RO
RCT: A Robot-Collected Touch-Vision-Language Dataset for Tactile Generalization
Jingbo He, Michael Färber and Roberto Calandra
For
robots manipulating open-world objects, tactile representations must generalize to unseen materials. We introduce RCT (Robotic Contact Tactile), a
robot-collected touch-
vision-
language dataset with 29,279 tactile frames from full
robot presses on 122 industrial reference materials in 7 categories, recorded with three DIGIT sensors at multiple contact positions. RCT preserves each press as a contact sequence, enabling held-out evaluation across materials, categories, sensors, contact positions, and contact sequences. Frames from one press are strongly correlated: frame-random splits can place near-duplicate observations of the same physical interaction in both training and test. With the encoder held fixed, removing contact-sequence overlap reduces tactile-to-text Recall@1 by 17.7 percentage points. When materials are additionally held out at training time, performance drops sharply, leaving held-out-material Recall@1 at 25.1 +/- 6.1% averaged over three held-out draws. The public TVL/HCT split shows the same structure: every test contact sequence appears in training, and raw-pixel nearest neighbors recover the correct sequence in 98.3% of cases. Uniformly sampling a press improves contrastive training, and RCT-trained
embeddings improve category probes on unseen materials. RCT makes contact-sequence-aware, held-out-material evaluation reproducible and exposes novel-material generalization as a central challenge for robotic tactile perception. The RCT
dataset is open-sourced at https://faerber-lab.github.io/RCT/
Read the full abstract ▾
Computation and Language · Cross-listed from cs.IR
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
Jiacheng Chen, Tao Zhang, Manxi Lin et al. (+26 more)
The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM
agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth
retrieval or ranking interfaces and leaving a gap between
language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for
retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol and exposes support surfaces for context access, catalog grounding, and state management. Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search
retrieval, listwise ranking, or product bundling. This model-centric design reduces lossy hand-offs between
agent orchestration and item-space execution. To build ShopX, we design semantically recoverable, LLM-operable SIDs and a training recipe that equips a general LLM for flexible multi-turn item-space fulfillment while retaining the knowledge and instruction-following abilities needed by a shopping
agent. We evaluate the ShopX framework against tool-mediated agentic systems on single- and multi-turn fulfillment tasks derived from anonymized Taobao production logs, showing that model-native fulfillment improves overall framework behavior, especially on complex or ambiguous requests.
Read the full abstract ▾
All authors Jiacheng Chen, Tao Zhang, Manxi Lin, Dunxian Huang, Teng Shi, Honghao Fu, Mengyan Li, Xinming Zhang, Chenchi Zhang, Xuan Lu, Xiaoxiong Du, Haibin Chen, Shaolin Ye, Hao Chang, Xiaoqi Li, Shuwen Xiao, Yujin Yuan, Jingxuan Feng, Shaopan Xiong, Huimin Yi, Ju Huang, Qiu Shen, Ying Chen, Junjun Zheng, Xiangheng Kong, Dan Ou, Haihong Tang, Yuning Jiang, Bo Zheng
Computation and Language
Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management
Luis Gasco, Hermenegildo Fabregat, Laura García-Sardiña et al. (+8 more)
This paper presents an overview of the second edition of the TalentCLEF challenge, organized as a Lab at the Conference and Labs of the Evaluation Forum (CLEF) 2026. TalentCLEF is an initiative aimed at advancing Natural
Language Processing research in Human Capital Management. The second edition of the challenge consisted of two tasks: Task A, contextualized job-person matching, focuses on identifying and ranking the most suitable candidates represented by their resumes for a given job vacancy in English and Spanish. Task B, job-skill matching with skill type classification, addresses retrieving the most relevant skills for a given job title in English and distinguishing between core and contextual skills. TalentCLEF attracted 113 registered teams and received more than 400 submissions in the two tasks, reflecting the growing interest of the research community in shared evaluation
benchmarks for Human Capital Management. This paper describes the motivation and organization of the challenge, summarizes the
datasets and evaluation settings, and reports the main results obtained by the participating teams.
Read the full abstract ▾
All authors Luis Gasco, Hermenegildo Fabregat, Laura García-Sardiña, Paula Estrella, Warre Veys, Casimiro Pío Carrino, Matthias De Lange, Daniel Deniz Cerpa, Álvaro Rodrigo, Jens-Joris Decorte, Rabih Zbib
Computation and Language
Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues
Mohammadamin Shafiei, Shuyue Stella Li and Yulia Tsvetkov
As large
language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behaviors are genuine or superficial. We show that current
fairness evaluations substantially overestimate moral safety. Models appear fair when demographic identity is stated as an explicit label, yet become measurably less fair when the same identity must be inferred. We term this failure performative compliance, where a model is fair when the presentation resembles a
fairness evaluation and less fair as that cue weakens. We introduce a cue-variation methodology that holds the moral dilemma and the demographic identity fixed and varies only how that identity is conveyed. Hiding the explicit label raises harmful decisions by +4.4 pp, changes model safety rankings, and the shift persists when models correctly infer the demographic, ruling out attribution error. We propose the Cue Visibility Gap, a model-agnostic robustness metric that can be added to any existing
fairness benchmark to separate genuine from performative moral safety.
Fairness evaluations that omit cue variation measure surface compliance, not moral robustness, and should not ground deployment decisions in high-stakes settings.
Read the full abstract ▾
Computation and Language
Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition
Kesego Mokgosi, Vukosi Marivate, Sitwala Mundia et al. (+3 more)
Southern Bantu
languages are spoken by over 80 million people, yet current foundation ASR models still produce zero-shot WER above 100%, which limits practical use in education and public services. We addressed this gap with a tone conditioned curriculum framework for 6 Southern Bantu
languages that combined hybrid difficulty scoring, gated adapters driven by tonal statistics and staged curriculum training. We trained on a community corpus and tested transfer to NCHLT to measure robustness beyond matched evaluation. Results revealed clear interactions between architecture and
language, with W2V-BERT outperforming Whisper on Nguni
languages by 3 to 4 WER points whilst Whisper performed better on Sotho-Tswana
languages. W2V-BERT with tone conditioning reached 28.41% average WER across
datasets and 23.79% on Xitsonga transfer. No single model suited all 6
languages, so deployment should pair model selection per
language with validation across corpora.
Read the full abstract ▾
All authors Kesego Mokgosi, Vukosi Marivate, Sitwala Mundia, Unarine Netshifhefhe, Tsholofelo Hope Mogale, Thapelo Sindane
Computation and Language
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
Ajmal M., Abin Roy, Afthab Salam Kanniyan et al. (+4 more)
Large
Language Models (LLMs) achieve strong results on many medical
benchmarks, but their clinical
reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical
reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical
reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recurring failure patterns: (i) verbosity bias, where GPT-4o-mini's diagnostic accuracy drops from 95.0% to 32.5% under information scarcity; (ii) a hidden knowledge paradox, where a specialist model reaches 92.5% maximum diagnostic potential but fails to retrieve that knowledge reliably in verbose contexts; and (iii) a 68.6%
reasoning-to-output mismatch, where correct diagnoses appear in
reasoning traces but are not reflected in final answers. We further evaluate the LLM-as-a-Judge paradigm on a human-verified failure set (n = 142). GPT-4o-mini approved 47.9% of clinically incorrect outputs, while HuatuoGPT-o1 approved all validly scored failures and showed a positive self-preference bias. These results suggest that standalone automated clinical evaluations can substantially overestimate clinical reliability without expert-grounded validation.
Read the full abstract ▾
All authors Ajmal M., Abin Roy, Afthab Salam Kanniyan, Jawadh Abdul Kabeer, Jerin James, Preslav Nakov, Zhuohan Xie
Computation and Language
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
Jonas Schäfer, Cezary Pilaszewicz and Gerhard Wunder
This work presents Dual-
Embedding Watermarking (DEW), a semantic watermarking scheme for large
language models (LLMs) that leverages contextual and
token-level
embeddings to enhance robustness against paraphrasing and translation. DEW utilizes a signal-processing methodology, applying algebraic vector-space operations to
token and context
embeddings to derive a watermark signal that degrades gracefully under semantic shifts. The method obfuscates the watermark by projecting
embedding vectors through pseudo-random
matrices seeded with a secret key. Experimental results show that dual-
embedding watermarking can offer state-of-the-art robustness, particularly against translation, while incurring relatively low computational overhead compared with other semantic schemes. At lower watermark strength, DEW also maintains competitive text quality, suggesting that dual-
embedding signals provide a promising substrate for robust semantic watermarking.
Read the full abstract ▾
Computation and Language
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Zhaojian Yu, Penghao Yin, Shuzheng Gao et al. (+3 more)
Training
language models (LMs) remains a highly human-intensive process, even as frontier
language model
agents become increasingly capable at software engineering and other long-horizon tasks. A central challenge is that autonomous post-training is not just a coding problem: it requires the
agent to repeatedly plan iterations, construct
benchmark-aligned data, run stable training jobs, evaluate checkpoints, and preserve experiment state across many hours of interaction. We present AutoTrainess, a LM
agent that exposes these operations as a repository of
agent-computer interfaces for planning, data preparation, training, evaluation, and logging. Rather than leaving the
agent to operate in a raw CLI environment with an underspecified action space, AutoTrainess externalizes prior human experience as explicit workflows, rules, and execution constraints that guide the
agent toward effective and reliable training behavior. On PostTrainBench, AutoTrainess consistently outperforms CLI-only baselines, achieving 26.94 average score with GPT-5.4 (Codex) versus 23.21 for CLI-only. It also generalizes across models and harnesses, improving DeepSeek-V4-Flash (OpenCode) from 12.13 to 19.58.
Read the full abstract ▾
All authors Zhaojian Yu, Penghao Yin, Shuzheng Gao, Shilin He, Kai Cai, Xiao-Ping Zhang
Computation and Language · Cross-listed from cs.AI
Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2
Johan Land
Large
language models can produce fluent, internally coherent
reasoning traces for abstract
reasoning tasks while still being confidently wrong - making selection among candidates, not just generation, the central challenge. I present a solver for ARC-AGI-2, a few-shot visual
reasoning benchmark, built around two principles: (i) treating
reasoning modalities as search operators, generating diverse candidates independently across text, image, and code channels, and (ii) context-preserving holistic judging, in which a judge model jointly compares all candidate
reasoning traces within a single long-context
prompt. Unlike self-consistency or majority voting, this approach reliably recovers correct minority hypotheses on tasks where the modal answer is wrong. On the ARC Prize semi-private evaluation set, the solver achieves 72.9 percent at USD 38.99 per task - the highest score on the verified leaderboard at the time of writing, exceeding the best standalone frontier models, GPT-5.2 Pro at 54.2 percent and Gemini 3 Pro at 54.0 percent, by +18.7 percentage points. On the public evaluation set, it achieves 76.1 percent at USD 19.69 per task. I release the full source code and document extensive negative results, including the finding that prescriptive prompting templates and iterative refinement systematically reduce hypothesis diversity and degrade performance.
Read the full abstract ▾
Computation and Language
FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents
Muhammad Usman Safder, Ayesha Gull, Rania Elbadry et al. (+6 more)
Large
Language Models (LLMs) are increasingly deployed as autonomous financial
agents initialized with explicit behavioral mandates such as "preserve capital" or "avoid speculative bets" that are meant to govern every decision throughout deployment. In practice, however, as
market context accumulates over long horizons, these mandates gradually lose their behavioral influence, a phenomenon we formalize as Mandate Salience Decay (MSD). To measure MSD objectively, we introduce FinPersona-Bench, a simulation
benchmark in which a synthetic
market decouples observable price from hidden fundamental value, enabling falsifiable evaluation across three failure modes: trading without signal in calm
markets, panic-selling during crashes, and ignoring fundamental value during speculative bubbles. Evaluating 18 leading frontier and open-source LLMs, each assigned one of three behavioral profiles ranging from strict capital preservation to aggressive growth, shows that MSD compounds over time and is model-dependent. In crash scenarios, the behavioral gap between static
agents and those receiving periodic mandate re-grounding grows 4.4x from the first to the final quarter of the simulation. The effects of mandate re-grounding are not uniformly positive: it consistently helps conservative
agents in low-signal
markets but actively worsens behavior for aggressive
agents in the same setting. These findings suggest that reliable long-horizon deployment requires selective, mandate-aware re-grounding based on
agent profile and
market regime.
Read the full abstract ▾
All authors Muhammad Usman Safder, Ayesha Gull, Rania Elbadry, Fan Zhang, Yankai Chen, Xueqing Peng, Xue Liu, Preslav Nakov, Zhuohan Xie
Computation and Language · Cross-listed from cs.LG
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
Wenhao Li, Jinhao Dong, Hailin Zhang et al. (+3 more)
Long-context Large
Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse
attention methods often suffer from static fixed-budget (Top-k)
retrieval or rely on proxy scores that are computationally expensive and biased. To address these limitations, we propose RaBitQCache, a novel sparse
attention framework that utilizes randomized rotated binary quantization and high-throughput binary-INT4 arithmetic to efficiently estimate
attention weights. Our proxy score serves as an unbiased
estimator with a proven error bound, enabling adaptive Top-p
retrieval that dynamically adjusts the
token budget based on actual
attention sparsity. We further implement a hardware-aware system with asynchronous pipelining and lazy updates to mask overhead. Evaluations demonstrate that RaBitQCache significantly accelerates inference and reduces
memory I/O while preserving generation quality compared to state-of-the-art baselines. Code is available at https://github.com/Sakuraaa0/RaBitQCache.git.
Read the full abstract ▾
All authors Wenhao Li, Jinhao Dong, Hailin Zhang, Wenhang Shi, Wei Lu, Xiaoyong Du
Computation and Language · Cross-listed from cs.SE
Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models
Mehmet Iscan
In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism. From a Popperian view, a generated program is a
conjecture and a test-execution violation is an oracle-relative, executable counterexample, so feedback's value should be attributed not to re-exposure to failing code but to whether the
conjecture is opened to external, executable criticism. As the third stage of a falsification-centered measurement program, this study builds a placebo-controlled instrument that decomposes the feedback packet against a blind-resampling baseline at matched output-generation budget and against content-free, shape-matched placebos. The contribution is not a new repair
algorithm but a reflexive methodology (packet decomposition, placebo mirroring, matched-budget discordant-pair tests, fresh-generation confirmation, executable audits) that makes both the model's program
conjecture and the researcher's "feedback content works" claim falsifiable. Across six HumanEval+/MBPP+
cells with three 0.5B-1.5B frozen models, 290 dead task-
cell units (no best-of-8 candidate passing the public tier) were evaluated; the main run produced 7,000 fresh generations and a preregistered follow-up 1,400 more. Blind resampling exceeded bare-code retry by +18 net unlocks (25/7, Holm p=0.0021). Code-plus-facts recovered +18 over bare code (21/3, p=0.00042) and +15 over a generic-bullet placebo (p=0.0041). An instruction-only effect was not distinguishable (+3, p=0.36). Code-plus-facts and blind resampling tied at 26 unlocks each (not equivalence). Six external-controller follow-ups tied a content-free shape placebo. In this regime, falsification helped not as vocabulary or self-critique, but as comparison with external, executable counterexamples.
Read the full abstract ▾
Computation and Language
Building an ASR Solution for Training and Assessing Children's Reading
Yacouba Diarra, Nouhoum Souleymane Coulibaly, Mamadou Dembele et al. (+2 more)
Automatic
speech recognition for children's reading remains underdeveloped for most African
languages, including Bambara, despite its potential value for reproducible literacy assessment. We present an open-source system for assessing children's reading in Bambara, developed through an end-to-end process linking field data collection,
benchmark construction, model adaptation, a reading application, and classroom validation. A mobile collection and assessment app was used to collect 55 hours of raw reading
speech from 60 children, from which we construct a public
benchmark for Bambara child-reading assessment. Fine-tuning experiments compare Soloni, a Bambara-adapted Fast-Conformer ASR framework with TDT and CTC decoders, with QuartzNet, a compact convolutional ASR architecture. The best Soloni model reduces WER from 0.42 to 0.22 and CER from 0.15 to 0.08, substantially outperforming QuartzNet on the isolated
benchmark. The experiments further show that repeated readings of the same texts provide architecture-dependent benefits: they substantially improve QuartzNet but add only marginal gains for Soloni, while SpecAugment regulates training without exceeding the best unaugmented configuration. Disaggregated analysis identifies children under 10 as the main source of residual errors, motivating targeted collection from younger readers. Ten classroom trials supported continued use of the application.
Read the full abstract ▾
All authors Yacouba Diarra, Nouhoum Souleymane Coulibaly, Mamadou Dembele, Aymane Dembele, Michael Leventhal