Computation and Language · Cross-listed from cs.LG
Gefen: Optimized Stochastic Optimizer
Nadav Benedek, Tomer Koren and Ohad Fried
AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training
memory, increasing the cost of large-scale pretraining. We propose Gefen, a
memory-efficient optimizer that automatically shares second-moment estimates across parameter blocks and quantizes the first moment using a learned codebook. Gefen reduces AdamW's optimizer
memory footprint by up to 8x while maintaining performance, saving 6.5 GiB per billion parameters. Prior work shares second moments across parameters grouped along the Hessian's block-diagonal structure, but relies on hand-specified architectural rules and leaves unexplained why such grouping works. We prove that large mixed Hessian entries constrain the ratio of squared gradients toward one, explaining why shared second moments are accurate when the squared gradients they pool are similar. The Hessian need not be computed: its block structure is inherited by squared gradients, allowing blocks to be found directly. Gefen therefore infers block structure from initial squared gradients, requiring no architecture-specific metadata or user-tuned hyperparameters beyond AdamW defaults. Gefen learns an exact histogram-based dynamic-programming quantization codebook and reuses the blocks for first-moment scaling. Across diverse pretraining experiments, Gefen achieves the lowest peak optimizer
memory among compared methods that maintain AdamW-level performance. In single-machine and distributed training, the reduced footprint enables larger microbatches and substantially improves throughput over AdamW, making Gefen a drop-in replacement that can train larger models or use larger global batch sizes. We provide the complete Python implementation, including fused CUDA kernels at https://github.com/ndvbd/Gefen
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Natively Unlearnable Large Language Models
Gaurav R. Ghosal, Pratyush Maini and Aditi Raghunathan
Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model. Isolating source contributions to disjoint parameters makes removal easier, though it obstructs joint learning across sources. We propose NULLs (Natively Unlearnable LLMs), a model class that satisfies the two opposing goals of isolating source-specific contributions and learning jointly across sources, by training a set of shared backbone
neurons alongside a pool of sparsely activated sinks. During training, information specific to a source naturally concentrates in its sinks while information shared across sources accumulates in the backbone. A source is then unlearned at deployment by disabling its corresponding sinks, with no gradient updates and no access to the retained data. We show that NULLs scales to Wikipedia's ~6M articles, isolating each as an independent source. Unlearning a single article removes knowledge specific to it while preserving facts shared with semantically related articles, closely matching retraining from scratch. We note that unlearning with NULLs is also robust: in a case study of unlearning the Harry Potter books, NULLs resists both
adversarial extraction and relearning that reverses post-hoc unlearning. Finally, NULLs preserves general
language capabilities, matching a standard
transformer on downstream
benchmarks. Together, these results suggest that source-level unlearning need not be an afterthought. It can be built natively into LLM training while retaining the benefits of shared representation learning.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
SuperThoughts: Reasoning Tokens in Superposition
Zheyang Xiong, Shivam Garg, Max Yu et al. (+4 more)
Long Chain-of-Thought (CoT)
reasoning improves LLM problem-solving but is computationally expensive due to sequential
token generation. While recent works explore
reasoning in continuous latent spaces to bypass discrete
token generation, they often struggle with training stability and fail to scale to complex, long-horizon tasks due to lack of supervision signal. We propose SuperThoughts, which compresses pairs of consecutive CoT
tokens into single latent representations and decodes two
tokens per step via a lightweight Multi-
Token Prediction (MTP) module. This preserves discrete
token supervision at training time while doubling throughput at inference time. We finetune Qwen2.5-Math-1.5B-Instruct, Qwen2.5-Math-7B-Instruct, Qwen2.5-Math-14B-Instruct, and evaluate on MATH500, AMC, OlympiadBench, and GPQA-Diamond. With a confidence-based adaptive mechanism that falls back to standard decoding when uncertain, SuperThoughts achieves $\sim$20–30% CoT length reduction while maintaining accuracy with minimal degradation (1-2 points accuracy drop on most tasks).
Read the full abstract ▾
All authors Zheyang Xiong, Shivam Garg, Max Yu, Vaishnavi Shrivastava, Haoyu Zhao, Anastasios Kyrillidis, Dimitris Papailiopoulos
Computation and Language
Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling
Ivan Kankeu
Neural topic models enable scalable semantic discovery, but their integration with
quantum hardware remains largely unexplored. We present a proof-of-concept hybrid classical-
quantum variational autoencoder (VAE) for topic modeling,
embedding parameterized
quantum circuits within the VAE inference network while retaining a classical topic-word decoder. To address the resource constraints of
quantum hardware, we propose a modified Gaussian Softmax posterior that decouples latent space dimensionality from the number of topics to be extracted, enabling the model to operate with a low-resource 10-
qubit quantum device. On the AgNews
dataset, the hybrid VAE outperforms state-of-the-art neural topic models (NTMs), reaching a $C_v$ coherence score of 0.71 and an NPMI score of 0.20 while preserving high topic diversity. For comparison, we also construct a fully classical variant, which also outperforms state-of-the-art models on AgNews and exhibits clear class separation in the latent space. These results demonstrate that hybrid VAEs are computationally viable even on NISQ-era devices and represent a promising direction for
quantum-enhanced topic modeling.
Read the full abstract ▾
Computation and Language
When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation
Gustavo H. Santos, Aline Carneiro Viana and Thiago H. Silva
LLM-based generative
agents are increasingly used in urban simulators, yet it remains unclear whether they reproduce empirically realistic human mobility patterns or merely generate plausible mobility narratives. We introduce a validation framework for evaluating the mobility of generative
agents of LLM-based urban simulators against real-world mobility data. For this, we use mobility laws, temporal rhythms, network motifs, semantic activity transitions, and behavioral mobility profiles. Using
datasets from the Greater Paris region and Shanghai, we evaluate AgentSociety and CitySim across multiple dimensions of mobility realism. Our analysis reveals a substantial gap between narrative plausibility and empirical mobility realism. Although the simulators capture some high-level semantic activity distributions, they struggle to reproduce core spatial and temporal constraints, including realistic trip-length distributions, origin-destination flows, dwell times, and transition dynamics. We further observe that realistic mobility diversity is unstable across default prompting configurations and may require explicit profile-aware initialization. To support reproducible evaluation, we also contribute scalable and open LLM-driven infrastructure for regional-scale map generation, observability-enhanced simulation, mobility-metric computation, and traffic simulation. Our findings highlight the need for rigorous empirical validation of LLM-based urban simulators and provide practical tools for building more realistic and reproducible urban simulation systems.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Poker Arena: Multi-Axis Profiling of Strategic Reasoning and Memory in LLMs
Pratham Singla, Shivank Garg and Vihan Singh
Strategic
reasoning under uncertainty underpins consequential decisions in negotiation, finance, and policy, but prevailing game-play
benchmarks collapse heterogeneous
reasoning dimensions into a single scalar, leaving the capability structure of frontier LLMs unexamined. We introduce Poker Arena, a no-limit Texas Hold'em tournament platform that couples a three-layer
memory architecture (within-hand, session, and cross-session) with a nine-axis cognitive profile decomposing strategic
reasoning into interpretable dimensions such as bet-sizing calibration and positional awareness. We evaluate seven frontier models across 50 sessions of 1,000 hands and a controlled
memory ablation; tournament chips and aggregate axis score order the field differently: Claude Opus 4.6 wins +$15,730 chips with 14 first-place finishes, yet ranks only fifth of seven on mean axis score, while persistent
memory helps some models and hurts others. These findings show that multi-axis evaluation surfaces capability structure that scalar leaderboards systematically misrank, with cross-dimensional consistency outweighing peak performance on any single axis.
Read the full abstract ▾
Computation and Language
The Culture Funnel: You Can't Align What isn't in the Data
Ananya Sahu, Mehrnaz Mofakhami, Daniel D'Souza et al. (+3 more)
Current cultural
alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer from a cultural data funnel. Using a multidimensional tagging framework across pretraining, fine-tuning,
alignment, and
reasoning datasets, we show explicit cultural signals decline sharply during post-training, while geographically concentrated, task-specialized data dominates. Multilinguality enhances geographic diversity of cultural knowledge but does not ensure balanced representation. Our tags improve downstream cultural
benchmark performance, demonstrating that advances require shifting focus in training data pipelines. To facilitate future research, we release our culturally tagged
dataset with 5.6M samples at https://huggingface.co/
datasets/CohereLabs/CultureMarkers.
Read the full abstract ▾
All authors Ananya Sahu, Mehrnaz Mofakhami, Daniel D'Souza, Thomas Euyang, Julia Kreutzer, Marzieh Fadaee
Computation and Language
QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoning
Abdessalam Bouchekif, Somaya Eltanbouly, Samer Rashwani et al. (+5 more)
This paper presents a comprehensive overview of the QIAS 2026 shared task, organized as part of the OSACT7 Workshop and co-located with LREC 2026. The shared task was designed to evaluate the ability of large
language models to perform complex
reasoning in the religious and legal domain of Islamic inheritance. Unlike conventional question-answering
benchmarks, QIAS 2026 focuses on end-to-end
reasoning from natural
language cases, requiring systems to perform the full inheritance calculation process, from identifying the eligible heirs to assigning the correct share to each beneficiary. To support this evaluation, the task was based on the MAWARITH
benchmark, a
dataset of $12{,}500$ Arabic inheritance cases annotated with intermediate
reasoning steps and final answers. System submissions were evaluated using MIR-E, a multi-step metric that measures performance across the main stages of inheritance
reasoning. A total of $16$ teams participated in the shared task, investigating a range of approaches, including prompting-based methods,
retrieval-augmented generation, and fine-tuning strategies. The results show that Islamic inheritance remains a highly challenging
benchmark for current
language models, especially in stages that require precise legal interpretation and structured numerical
reasoning. This overview summarizes the task design,
dataset, evaluation framework, participating systems, and main results.
Read the full abstract ▾
All authors Abdessalam Bouchekif, Somaya Eltanbouly, Samer Rashwani, Shahd Gaben, Mutaz Al-Khatib, Heba Sbahi, Emad Mohamed, Mohammed Ghaly
Computation and Language
Which Models Perform Better in Inheritance Reasoning?
Mohammed Amine Mouhoub and Chahinez Bouchekif
This paper presents the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance
reasoning. The task evaluates the ability of large
language models to solve inheritance cases that require legal interpretation, multi-step
reasoning, and precise numerical computation. We compare commercial and open-source models under a unified prompting strategy to assess their effectiveness in structured legal
reasoning with minimal task-specific adaptation. \\ Our results show a clear gap in reliability between the two model families. Commercial models demonstrate stronger performance in identifying eligible heirs, applying exclusion rules, and maintaining consistency across
reasoning steps. In contrast, open-source models exhibit greater instability, particularly in cases involving dependent legal decisions and fractional share adjustments. The best performance is achieved by Gemini 2.5 Flash, with an MRE of $0.989$.
Read the full abstract ▾
Computation and Language
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jundong Xu, Qingchuan Li, Jiaying Wu et al. (+11 more)
Large
language model (LLM)
agents have achieved strong performance on a wide range of
benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring
agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a
benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based
memory paradigm that records
memory evolution as structured update histories, enabling
agents to reason about environmental
evolution through changes in their
memory. Experiments show that current
agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard
benchmarks such as
GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the
memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling
evolution in both evaluation and
memory for reliable
agent deployment.
Read the full abstract ▾
All authors Jundong Xu, Qingchuan Li, Jiaying Wu, Yihuai Lan, Shuyue Stella Li, Huichi Zhou, Bowen Jiang, Lei Wang, Jun Wang, Anh Tuan Luu, Caiming Xiong, Hae Won Park, Bryan Hooi, Zhiyuan Hu
Computation and Language
Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
Zilin Xiao, Qi Ma, Chun-cheng Jason Chen et al. (+4 more)
Retrieval-augmented generation (RAG) has become a standard mechanism for grounding
language models in external knowledge, yet conventional
retrieval based on lexical or semantic similarity is poorly suited for complex
reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying
reasoning pattern. We propose
Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that teaches
language models to reason by analogy. RA-RFT uses gold-relevance
distillation to train a retriever that ranks contexts by expected
reasoning benefit rather than semantic overlap, and then fine-tunes the policy model via reinforcement fine-tuning methods with retrieved analogous demonstrations, so the model learns to leverage
reasoning traces under verifiable outcome rewards. We further analyze the diversity of retrieved contexts and find that
reasoning-aware
retrieval surfaces complementary solution strategies that provide distinct
reasoning scaffolds for individual problems. Across challenging mathematical
reasoning benchmarks, RA-RFT consistently outperforms standard reinforcement fine-tuning methods. For example, it improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively – suggesting that
reasoning-aware
retrieval is a complementary axis of improvement and orthogonal to advances in reward design or training curricula.
Read the full abstract ▾
All authors Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen, Avinash Atreya, Hanjie Chen, Vicente Ordonez
Computation and Language
Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution
Dimitri Kachler, Damien Sileo and Pascal Denis
With the growth of LLMs' (Large
Language Models) capabilities, there has been an increasing push to curate high quality
datasets by filtering samples in the training data. In general, Data Attribution (DA) methods aim to estimate how individual samples in a training
dataset can precondition a model to generate certain outputs. As an example, one might be interested in which samples in the data could be the source of toxic behavior after training the LLM. Many methods quantify this conditioning through the paradigm of influence functions. While methods of this family are effective in its function, they lack the necessary processing speed and storage compactness to be practically implemented on large
datasets. We propose a method, Influcoder, as a quick and cost-effective approach to influence-based Data Attribution at scale.
Read the full abstract ▾
Computation and Language
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
Yaxin Du, Yifan Zhou, Yujie Ge et al. (+7 more)
Tool-augmented LLM
agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main
reasoning trace. This creates an execution-granularity mismatch: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce HyperTool, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69% to 35.29% on Qwen3-32B and from 9.93% to 33.33% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.
Read the full abstract ▾
All authors Yaxin Du, Yifan Zhou, Yujie Ge, Jiajun Wang, Xianghe Pang, Shuo Tang, Tuney Zheng, Bryan Dai, Jian Yang, Siheng Chen
Computation and Language · Cross-listed from cs.AI
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Amy Xin, Jiening Siow, Junjie Wang et al. (+5 more)
LLM-based
agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing
agent workflows to designing
agent environments: the resources, constraints, and interfaces that shape
agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-
agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered
agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded
agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research
agents.
Read the full abstract ▾
All authors Amy Xin, Jiening Siow, Junjie Wang, Zijun Yao, Fanjin Zhang, Jian Song, Lei Hou, Juanzi Li
Computation and Language
Operadic consistency: a label-free signal for compositional reasoning failures in LLMs
Nathaniel Bottman, Yinhong Liu and Kyle Richardson
Detecting LLM
reasoning failures at inference time without ground-truth labels has motivated a wide range of confidence baselines, including self-consistency, semantic
entropy, and P(True), built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces by composing a stated decomposition of the same query. We instantiate this idea as operadic consistency (OC), a per-question signal. Across twelve instruction-tuned LLMs (4B to 671B parameters, open-weights and closed-source) on four multi-hop QA
datasets, OC is strongly correlated with accuracy on every
dataset (Pearson $r \in [0.86, 0.94]$, all $p \leq 0.0004$), and is the only signal we evaluate with $r \geq 0.85$ uniformly across all four
datasets. Chain-of-thought self-consistency (CoT-SC; Wang et al., 2023) matches OC on HotpotQA and DROP ($r = 0.93, 0.87$) but drops to $r \approx 0.45$ on MuSiQue and StrategyQA. At the per-question level, OC contributes information beyond CoT-SC and semantic
entropy on every
dataset (cluster-robust $p \leq 10^{-16}$ for the OC coefficient), and the conclusion is robust to additionally controlling for constructed decomposition-aware baselines ($p \leq 10^{-13}$). The same signal yields selective-prediction improvements (accuracy at fixed coverage) over a tuned CoT-SC baseline at the equal-cost $K = 3$ budget (AUARC lifts of +0.086 to +0.096 and AUROC lifts of +0.092 to +0.164; 95% CIs exclude zero on every
cell). On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction point-estimate lift on all 16 (
dataset, budget, metric)
cells tested, with 95% CIs excluding zero on 12 of the 16.
Read the full abstract ▾
Computation and Language
SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation
Marek Šuppa, Andrej Ridzik, Daniel Hládek et al. (+2 more)
We introduce SkMTEB, the first comprehensive MTEB-style text
embedding benchmark for Slovak, a low-resource West Slavic
language, comprising 31
datasets across 7 task types – nearly 4$\times$ the depth of existing
multilingual benchmark coverage for Slovak. Our evaluation of 31
embedding models reveals that large instruction-tuned
multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to
embedding tasks. To address the need for efficient, locally-deployable Slovak
embeddings, we develop e5-sk-small (45M parameters) and e5-sk-large (365M) by applying vocabulary trimming and fine-tuning to
Multilingual E5 models. Despite size reductions of up to 62%, our open-source models achieve competitive performance with proprietary APIs while remaining locally deployable for semantic search and
retrieval-augmented generation (RAG). We release the
benchmark, models,
datasets, and code openly, hoping our approach offers a replicable path for other under-resourced
languages.
Read the full abstract ▾
All authors Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková, Viktória Ondrejová
Computation and Language
Recursive Agent Harnesses
Elias Lumer, Sahil Sen, Kevin Paul et al. (+1 more)
Recursive
language models (RLMs) showed that recursion over model calls is an effective strategy for long-context
reasoning, and production coding
agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic workflows. We name and study the pattern between these two lines of work, where the recursive unit is a full
agent harness with filesystem tools, code execution, and planning rather than a model call with no tools. We call this the Recursive
Agent Harness (RAH) and frame it as harness recursion, the code-first extension to the model recursion of RLMs. A parent
agent generates and runs an executable script that spawns subagent harnesses in parallel for fine-grained workloads and uses structured function calls for small subtasks. We provide a controlled evaluation on long-context
reasoning. With the backbone held fixed at GPT-5 to match the published Codex and RLM baselines, RAH improves the Codex coding-
agent baseline from 71.75% to 81.36% on Oolong-Synthetic (199 samples, 13 context-length buckets up to 4M
tokens), a gain attributable to the harness rather than the model. With a stronger backbone, Claude Sonnet 4.5, the same design reaches 89.77%.
Read the full abstract ▾
All authors Elias Lumer, Sahil Sen, Kevin Paul, Vamse Kumar Subbiah
Computation and Language
Operads for compositional reasoning in LLMs
Nathaniel Bottman and Kyle Richardson
Question decomposition, i.e. breaking a complex query into simpler sub-queries whose answers are composed to produce a final answer, is a widely used strategy for improving LLM
reasoning, yet it currently lacks a rigorous mathematical foundation. In this paper, we propose operads, mathematical structures that model many-in, one-out operations and compositions thereof, as a natural framework for describing question decomposition. We define the questions operad $Q$, in which operations correspond to question templates and composition corresponds to substitution of sub-answers, and show how QA models can be interpreted as
algebras over $Q$. Beyond reframing existing practice, this operadic perspective points toward new methods, in particular a notion of operadic consistency, which measures whether a QA model's answers agree across the partial collapses of a question decomposition tree. Empirical evaluation of operadic consistency is reported in our companion paper (Bottman, Liu, and Richardson, 2026), which finds it strongly correlated with accuracy across twelve LLMs and four multi-hop QA
datasets and outperforming standard temperature-based self-consistency baselines. We argue that operads are the natural mathematical home for question decomposition, and that invariants such as operadic consistency open new directions for analyzing and improving the reliability of multi-step
reasoning.
Read the full abstract ▾
Computation and Language
From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
Pedro Correa, Olivier Perrotin, Samir Sadok et al. (+2 more)
The choice of
speech representation is critical in
speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four
speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units and to articulatory deformations. We found that encoding phonetic classes is beneficial for accurate facial animation prediction on both semantic and label-based representations with comparable facial animation quality. From the latter, we introduce an Audio Visual Text-to-
Speech (AVTTS) pipeline that leverages, as a shared space, discrete representations to decode
speech and 3D facial motion.
Read the full abstract ▾
All authors Pedro Correa, Olivier Perrotin, Samir Sadok, Paula Costa, Thomas Hueber
Computation and Language
Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models
Jialin Gan, Xin Qiu, Guangzhe Chen et al. (+1 more)
Large
language models (LLMs) have enabled time series (TS) analysis by jointly modeling numerical observations and textual context through a shared
token interface. However, TS
tokens and
prompt tokens exhibit fundamentally different information structures, making uniform
token processing inefficient. In this paper, we study
token efficiency in TS
language modeling from an asymmetric-
token perspective. We show that TS
tokens have highly uneven spectral contributions, where many
tokens share redundant frequency patterns while a small subset preserves critical temporal evidence. We also observe that
prompt-
token influence attenuates with model depth, suggesting that full
prompt retention across all layers is unnecessary. Based on these findings, we develop an adaptive
token budgeting framework that compresses TS
tokens via frequency-domain structure and progressively reduces
prompt tokens across layers. Experiments across
forecasting, classification, imputation, and anomaly detection demonstrate up to \textit{\textbf{7.68$\times$}} inference acceleration and performance gains in \textit{78%} of evaluated settings, showing the effectiveness of asymmetric
token compression for scalable TS foundation models.
Read the full abstract ▾
All authors Jialin Gan, Xin Qiu, Guangzhe Chen, Xue Wang
Computation and Language
One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders
Minghao Luo and Liang Chen
Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM recommenders may consume web content that Generative Engine Optimization (GEO) operators have polluted to mislead them. We ask: to what extent do they become unwitting promoters of fake products? We introduce FORGE (Fake Online Recommendations in Generative Environments), which locally rewrites real products in a frozen set of retrieved web pages into fake ones and measures how often the LLM recommends the fake product, across 225 real products in 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies across categories, increasing when models lack stable prior knowledge of the products.
Reasoning does not mitigate this vulnerability; instead, it often generates spurious social proof to justify false recommendations. None of the four defenses is adequate: the skepticism
prompt can exacerbate vulnerability much like
reasoning, the two consensus filters risk suppressing legitimate products, and credibility re-ranking helps every model but removes only a sixth of the fakes. We release the FORGE
benchmark and the evaluation code at https://github.com/leoluolol/forge-
benchmark.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
Daniel Scalena, Sara Candussio, Luca Bortolussi et al. (+3 more)
Chain-of-thought (CoT)
reasoning is the dominant paradigm for inference-time scaling in
language models, yet the causal influence of individual steps on the final answer remains poorly understood. In this work, we use answer logits at the end of each
reasoning step to estimate each step's causal importance to the final answer and intermediate guesses, shedding light on the answer formation process of several
reasoning model families. Across diverse tasks, we find that
reasoning typically crosses a commitment boundary, a sharp transition from transient intermediate guesses to a stable, high-confidence answer. This transition often happens in a single step, well before the model's
reasoning block ends, and is followed by epiphenomenal CoT steps that leave the final answer probability unaltered. Using
attention probes, we show that answer-formation stages can be linearly decoded from the activations of intermediate
reasoning steps with high accuracy, showing robust generalization to unseen
reasoning tasks. We leverage this property for early-exiting
reasoning blocks at the commitment boundary location, reducing the length of CoTs up to 55% with negligible impact on model performance.
Read the full abstract ▾
All authors Daniel Scalena, Sara Candussio, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti
Computation and Language · Cross-listed from cs.AI
Reward Modeling for Multi-Agent Orchestration
King Yeung Tsang, Zihao Zhao, Vishal Venkataramani et al. (+5 more)
Multi-
Agent Systems (MAS) built on Large
Language Models (LLMs) require effective orchestration to coordinate specialized
agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-
agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-
agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in
token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical
reasoning, web-based question answering, and multi-hop
reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-
agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.
Read the full abstract ▾
All authors King Yeung Tsang, Zihao Zhao, Vishal Venkataramani, Haizhou Shi, Zixuan Ke, Semih Yavuz, Shafiq Joty, Hao Wang
Computation and Language · Cross-listed from cs.CY
The Tone of Awareness: Topic, Sentiment, and Toxicity Maps During Mental Health Month on TikTok
Henrique Ferraz de Arruda, Andreia Sofia Teixeira, Pranay Gundala Reddy et al. (+3 more)
Despite raising concerns about the mental health effects associated with the usage of TikTok, little is known about how related content is framed by creators and received by audiences. We collect the content of 28,341 TikTok
videos and 80,130 comments from Mental Health Awareness Month (May) in 2023 and 2024 via the TikTok Research API, and study how the tone of awareness varies across topics and years. We characterize "tone" as the emotional and interpersonal framing of mental health discourse, operationalized through sentiment and toxicity measures. We extract topics from
video text using BERTopic and log-odds keywords, then quantify topic-conditioned sentiment (XLM-T) and toxicity (Detoxify) separately for
video transcriptions and comments. Sentiment captures the affective valence of content, while toxicity reflects the presence of harmful or abusive
language. We find a stable set of recurring themes across years, spanning clinical conditions, emotional disclosure, self-care, and campaign-oriented content, with engagement highly skewed toward a small subset of topics. All sentiment and toxicity analyses are computed separately for
video content and comments, allowing us to distinguish between content production and audience reception. Sentiment in
videos is often negative for emotionally charged topics, while comments tend to shift toward more mixed or positive polarity, especially for suicide prevention. Toxicity is low in median overall, but exhibits longer-tailed outliers in comments than in
videos that are more pronounced in comments and concentrated in specific topics (e.g., "Duet", "Suicide Prevention", and "Psychisch"). Overall, our results provide a topic-level decomposition of mental health discourse on TikTok during awareness-month campaigns.
Read the full abstract ▾
All authors Henrique Ferraz de Arruda, Andreia Sofia Teixeira, Pranay Gundala Reddy, Anindya Mondal, Kleber Andrade Oliveira, Filipi Nascimento Silva
Computation and Language
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Baochang Ren, Xinjie Liu, Xi Chen et al. (+15 more)
Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator.
Vision-
Language-Action (VLA) models provide one possible interface between written protocols and
robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent
liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse
robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported
robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action
token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia
benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.
Read the full abstract ▾
All authors Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen
Computation and Language
Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya et al. (+2 more)
Multimodal Large
Language Models (MLLMs) have shown promising
reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in
multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic
languages and rely on
multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale
multilingual multimodal medical question-answer
dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian
languages. We further propose ArogyaSutra, an actor-critic-based multi-
agent framework that integrates tool grounding with dual-
memory mechanisms for step-wise,
reasoning-aware decision making, and uses stored actor-critic simulation trajectories for
distillation. Experiments show that our
dataset and framework improve
multilingual medical
reasoning accuracy across all Indic
languages, with ablations validating the contribution of each component. The source code and
dataset are available at: https://iitp-cse.github.io/ArogyaSutra/
Read the full abstract ▾
All authors Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya, Arijit Roy, Sriparna Saha
Computation and Language · Cross-listed from cs.CV
Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
Shengqiang Zhang, Ruotong Liao, Volker Tresp et al. (+2 more)
Text-guided image editing with visual autoregressive (VAR) generators requires controlling both what the model samples and where the sampled change is written back into the image code. Existing VAR editors mainly operate on
token streams, features, or flat next-
token logits, leaving two native structures of bitwise-residual VAR models underused: the per-bit Bernoulli prediction head and the additive multi-scale residual code field from which the image is assembled. We propose BitResEdit, a training-free editor for bitwise-residual VAR generators such as Infinity. BitEdit performs source-negative guidance by tilting the post-CFG per-bit log-odds along a source–target contrast computed on a shared edited prefix, then projects each update into a closed-form Bernoulli-KL trust region around the clean CFG sampler. ResEdit converts the sampled bits into per-scale continuous-code residuals, gates them with a localization mask, and re-injects them through the generator's native sum-of-scales. Together they couple decision-time bit guidance with combination-time code composition, so masked-out latent features are preserved exactly by code arithmetic while localized, scale-aware edits are applied inside the target region. On PIE-Bench with Infinity-2B, BitResEdit attains the strongest text
alignment among same-backbone VAR editors, improving CLIP on the edited region by +1.07 over the strongest prior editor while keeping background preservation competitive with it. Ablations show BitEdit and ResEdit play complementary roles in target
alignment and background preservation.
Read the full abstract ▾
All authors Shengqiang Zhang, Ruotong Liao, Volker Tresp, Barbara Plank, Hinrich Schütze
Computation and Language · Cross-listed from cs.AI
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
Hoin Jung and Xiaoqian Wang
Retrieval augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large
retrieval units preserve context but often introduce irrelevant content, which can dilute answer bearing evidence and worsen long context utilization. Fine-grained units are more compact, but they may be difficult to retrieve reliably because short chunks can lack semantic, lexical, or bridging cues needed to match the query. We propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid
retrieval framework that treats chunk granularity as query-specific reliability estimation. Instead of training a new retriever or modifying the generator, UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities. For each query, it converts each expert-granularity score list into an evidence distribution, estimates reliability from distribution
entropy, and fuses candidates according to query-specific semantic, lexical, and granularity confidence. We further introduce UMGP-RAG, a parent promotion variant that uses fine-grained hits to locate relevant evidence while returning broader non-redundant parent chunks for local coherence. Experiments on question answering
benchmarks show that uncertainty-aware fusion and parent promotion improve generation quality while maintaining a lightweight, plug-and-play
retrieval pipeline.
Read the full abstract ▾
Computation and Language · Cross-listed from eess.AS
Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
Soumyajit Mitra, Prabhat Pandey, Abhinav Jain et al. (+2 more)
Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based
agents, particularly under dynamic floor competition and varying user expectations. We propose ModeratorLM, a role-playing voice
agent that conditions turn-taking behavior on an explicitly assigned role in multi-party settings. The system is built on a
speech large
language model operating in chunk-wise streaming manner. We further introduce a
reasoning-augmented variant that incorporates chain-of-thought
reasoning over conversational context and the assigned role. We construct RolePlayConv, a large-scale synthetic
dataset of spoken multi-party conversations with diverse assistant roles. Experiments on real-world meeting data and RolePlayConv show improved turn-taking precision by over 40% and recall by more than 70%, while substantially reducing false-positive interruptions compared to non-role-conditioned baselines.
Read the full abstract ▾
All authors Soumyajit Mitra, Prabhat Pandey, Abhinav Jain, Shanmukha Sahith, K V Vijay Girish
Computation and Language
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
Tongyao Zhu, Chao-Ming Huang and Min-Yen Kan
While mixed-
language querying is ubiquitous in
multilingual communities, the sensitivity of dense retrievers to such queries remains poorly understood. We present a ratio-controlled study on mMARCO that systematically evaluates
retrieval performance by varying the mixing proportion of parallel query translations via
embedding-level mixing – constructing mixed queries as an interpolation of monolingual
embeddings. Experiments with BGE-M3 demonstrate that an optimal mixing ratio outperforms the best monolingual endpoint in 88/105 cases. We uncover a distinct asymmetry driven by English dominance: mixing is uniformly beneficial when retrieving from non-English document indices, whereas indices containing English are best served by pure English queries. Furthermore, English acts as the strongest mixing partner for every non-English document
language. Finally, when controlling for English dominance, mixing gains correlate negatively with typological distance. We conclude that
language-mix sensitivity is structured and predictable, and we validate the robustness of these patterns across model families and scales.
Read the full abstract ▾