Computation and Language
Time-Critical Multimodal Medical Transportation: Organs, Patients, and Medical Supplies
Elaheh Sabziyan Varnousfaderani, Syed A. M. Shihab and Mohammad Taghizadeh
Timely transportation of organs, patients, and medical supplies is critical to modern healthcare, particularly in emergencies and transplant scenarios where even short delays can severely impact outcomes. Traditional ground-based vehicles such as ambulances are often hindered by traffic congestion; while air vehicles such as helicopters are faster but costly. Emerging air vehicles – Unmanned Aerial Vehicles and electric vertical take-off and landing aircraft – have lower operating costs, but remain limited by range and susceptibility to weather conditions. A
multimodal transportation system that integrates both air and ground vehicles can leverage the strengths of each to enhance overall transportation efficiency. This study introduces a constructive greedy heuristic
algorithm for
multimodal vehicle dispatching for medical transportation. Four different fleet configurations were tested: (i) ambulances only, (ii) ambulances with Unmanned Aerial Vehicles, (iii) ambulances with electric vertical take-off and landing aircraft, and (iv) a fully integrated fleet of ambulances, Unmanned Aerial Vehicles, and electric vertical take-off and landing aircraft. The
algorithm incorporates payload consolidation across compatible routes, accounts for traffic congestion in ground operations and weather conditions in aerial operations, while enabling rapid vehicle dispatching compared to computationally intensive optimization models. Using a common set of conditions, we evaluate all four fleet types to identify the most effective configurations for fulfilling medical transportation needs while minimizing operating costs, recharging/fuel costs, and total transportation time.
Read the full abstract ▾
Computation and Language · Cross-listed from eess.AS
Abdoulaye Diack, Perry Nelson, Kwaku Agbesi et al. (+40 more)
The advancement of
speech technology has predominantly favored high-resource
languages, creating a significant digital divide for speakers of most Sub-Saharan African
languages. To address this gap, we introduce WAXAL, a large-scale, openly accessible
speech dataset for 24
languages representing over 100 million speakers. The collection consists of two main components: an Automated
Speech Recognition (ASR)
dataset containing approximately 1,250 hours of transcribed, natural
speech from a diverse range of speakers, and a Text-to-
Speech (TTS)
dataset with around 235 hours of high-quality, single-speaker recordings reading phonetically balanced scripts. This paper details our methodology for data collection, annotation, and quality control, which involved partnerships with four African academic and community organizations. We provide a detailed statistical overview of the
dataset and discuss its potential limitations and ethical considerations. The WAXAL
datasets are released at https://huggingface.co/
datasets/google/WaxalNLP under the permissive CC-BY-4.0 license to catalyze research, enable the development of inclusive technologies, and serve as a vital resource for the digital preservation of these
languages.
Read the full abstract ▾
All authors Abdoulaye Diack, Perry Nelson, Kwaku Agbesi, Angela Nakalembe, MohamedElfatih MohamedKhair, Vusumuzi Dube, Tavonga Siyavora, Subhashini Venugopalan, Jason Hickey, Uche Okonkwo, Abhishek Bapna, Isaac Wiafe, Raynard Dodzi Helegah, Elikem Doe Atsakpo, Charles Nutrokpor, Fiifi Baffoe Payin Winful, Kafui Kwashie Solaga, Jamal-Deen Abdulai, Akon Obu Ekpezu, Audace Niyonkuru, Samuel Rutunda, Boris Ishimwe, Michael Melese, Engineer Bainomugisha, Joyce Nakatumba-Nabende, Andrew Katumba, Claire Babirye, Jonathan Mukiibi, Vincent Kimani, Samuel Kibacia, James Maina, Fridah Emmah, Ahmed Ibrahim Shekarau, Ibrahim Shehu Adamu, Yusuf Abdullahi, Howard Lakougna, Bob MacDonald, Hadar Shemtov, Aisha Walcott-Bryant, Moustapha Cisse, Avinatan Hassidim, Jeff Dean, Yossi Matias
Computation and Language
Predicting first-episode homelessness among US Veterans using longitudinal EHR data: time-varying models and social risk factors
Rohan Pandey, Haijuan Yan, Hong Yu et al. (+1 more)
Homelessness among US veterans remains a critical public health challenge, yet risk prediction offers a pathway for proactive intervention. In this retrospective prognostic study, we analyzed electronic health record (EHR) data from 4,276,403 Veterans Affairs patients during a 2016 observation period to predict first-episode homelessness occurring 3-12 months later in 2017 (prevalence: 0.32-1.19%). We constructed static and time-varying EHR representations, utilizing clinician-informed logic to model the persistence of clinical conditions and social risks over time. We then compared the performance of classical machine learning,
transformer-based masked
language models, and fine-tuned large
language models (LLMs). We demonstrate that incorporating social and behavioral factors into longitudinal models improved precision-recall area under the curve (PR-AUC) by 15-30%. In the top 1% risk tier, models yielded positive predictive values ranging from 3.93-4.72% at 3 months, 7.39-8.30% at 6 months, 9.84-11.41% at 9 months, and 11.65-13.80% at 12 months across model architectures. Large
language models underperformed encoder-based models on discrimination but showed smaller performance disparities across racial groups. These results demonstrate that longitudinal, socially informed EHR modeling concentrates homelessness risk into actionable strata, enabling targeted and data-informed prevention strategies for at-risk veterans.
Read the full abstract ▾
All authors Rohan Pandey, Haijuan Yan, Hong Yu, Jack Tsai
Computation and Language · Cross-listed from cs.LG
Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
Xuemin Yu, Ankur Garg, Samira Ebrahimi Kahou et al. (+1 more)
Large
language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture. Latent concepts extracted from hidden states offer a promising direction for interpreting LLMs, but existing clustering-based methods face a trade-off: hierarchical clustering produces coherent concepts but is limited to small
datasets due to its quadratic
memory cost, while K-Means scales efficiently but may yield less semantically coherent concepts. We propose Vector Quantized Latent Concept (VQLC), a discrete concept learning framework that learns a codebook of latent concepts on frozen hidden states. Across 12
dataset-model settings, VQLC stays close to K-Means in computational cost, scales better than hierarchical clustering, and remains competitive in faithfulness, with the clearest gains on decoder-only models. LLMs-based evaluation, qualitative analysis, and a Sparse Autoencoder (SAE) comparison demonstrate that the learned concepts are interpretable and task-relevant.
Read the full abstract ▾
All authors Xuemin Yu, Ankur Garg, Samira Ebrahimi Kahou, Hassan Sajjad
Computation and Language · Cross-listed from cs.LG
Towards Understanding Steering Strength
Magamed Taimeskhanov, Samuel Vaiter and Damien Garreau
A popular approach to post-training control of large
language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along this direction at inference time. While many propositions exist to pick this direction, considerably less is understood about how to choose the magnitude of the move, whereas its importance is clear: too little and the intended behavior does not emerge, too much and the model's performance degrades beyond repair. In this work, we propose the first theoretical analysis of steering strength. We characterize its effect on next
token probability, presence of a concept, and cross-
entropy, deriving precise qualitative laws governing these quantities. Our analysis reveals surprising behaviors, including non-monotonic effects of steering strength. We validate our theoretical predictions empirically on eleven
language models, ranging from a small GPT architecture to modern models.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
BinaryPPO: Efficient Policy Optimization for Binary Classification
Punya Syon Pandey and Zhijing Jin
Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference. However, SFT often performs poorly in real-world settings with label noise, class imbalance, or sparse supervision. We introduce BinaryPPO, an offline reinforcement learning large
language model (LLM) framework that reformulates binary classification as a reward maximization problem. Our method leverages a variant of Proximal Policy Optimization (PPO) with a confidence-weighted reward function that penalizes uncertain or incorrect predictions, enabling the model to learn robust decision policies from static
datasets without online interaction. Across eight domain-specific
benchmarks and multiple models with differing architectures, BinaryPPO improves accuracy by 40-60 percentage points, reaching up to 99%, substantially outperforming supervised baselines. We provide an in-depth analysis of the role of reward shaping, advantage scaling, and policy stability in enabling this improvement. Overall, we demonstrate that confidence-based reward design provides a robust alternative to SFT for binary classification. Our code is available at https://github.com/psyonp/BinaryPPO.
Read the full abstract ▾
Computation and Language
InfMem: Learning System-2 Memory Control for Long-Context Agent
Xinyu Wang, Mingze Li, Peng Lu et al. (+6 more)
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict
memory constraints. While streaming
agents enable scalable processing, their passive
memory update strategy often fails to preserve low-salience bridging evidence required for multi-hop
reasoning. We propose InfMem, a control-centric
agent that instantiates System-2-style control via a PreThink-Retrieve-Write protocol. InfMem actively monitors evidence sufficiency, performs targeted in-document
retrieval, and applies evidence-aware joint compression to update a bounded
memory. To ensure reliable control, we introduce a practical SFT-to-RL training recipe that aligns
retrieval, writing, and stopping decisions with end-task correctness. On ultra-long QA
benchmarks ranging from 32k to 1M
tokens, InfMem consistently outperforms MemAgent across backbones. Specifically, InfMem improves average absolute accuracy by 10.17, 11.84, and 8.23 points on Qwen3-1.7B, Qwen3-4B, and Qwen2.5-7B, respectively, while reducing inference time by 3.9x on average and by up to 5.1x through adaptive early stopping. Code is available at https://github.com/UCMP13753/InfMem.
Read the full abstract ▾
All authors Xinyu Wang, Mingze Li, Peng Lu, Xiao-Wen Chang, Lifeng Shang, Jinping Li, Fei Mi, Prasanna Parthasarathi, Yufei Cui
Computation and Language
Monotonicity as an Architectural Bias for Robust Language Models
Patrick Cooper, Alireza Nadali, Ashutosh Trivedi et al. (+1 more)
Large
language models (LLMs) are known to exhibit brittle behavior under
adversarial prompts and jailbreak attacks, even after extensive
alignment and fine-tuning. This fragility reflects a broader challenge of modern neural
language models: small, carefully structured perturbations in high-dimensional input spaces can induce large and unpredictable changes in internal semantic representations and output. We investigate monotonicity as an architectural inductive bias for improving the robustness of
Transformer-based
language models. Monotonicity constrains semantic transformations so that strengthening information, evidence, or constraints cannot lead to regressions in the corresponding internal representations. Such order-preserving behavior has long been exploited in control and safety-critical systems to simplify
reasoning and improve robustness, but has traditionally been viewed as incompatible with the expressivity required by neural
language models. We show that this trade-off is not inherent. By enforcing monotonicity selectively in the feed-forward sublayers of sequence-to-sequence
Transformers – while leaving
attention mechanisms unconstrained – we obtain monotone
language models that preserve the performance of their pretrained counterparts. This architectural separation allows negation, contradiction, and contextual interactions to be introduced explicitly through
attention, while ensuring that subsequent semantic refinement is order-preserving. Empirically, monotonicity substantially improves robustness:
adversarial attack success rates drop from approximately 69% to 19%, while standard summarization performance degrades only marginally.
Read the full abstract ▾
All authors Patrick Cooper, Alireza Nadali, Ashutosh Trivedi, Alvaro Velasquez
Computation and Language
WideSeek: Advancing Wide Research via Multi-Agent Scaling
Ziyang Huang, Haolin Ren, Xiaowei Yuan et al. (+6 more)
Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the lack of dedicated
benchmarks and optimization methodologies for search breadth. To address these challenges, we take a deep dive into Wide Research from two perspectives: Data Pipeline and
Agent Optimization. First, we produce WideSeekBench, a General Broad Information Seeking (GBIS)
benchmark constructed via a rigorous multi-phase data pipeline to ensure diversity across the target information volume, logical constraints, and domains. Second, we introduce WideSeek, a dynamic hierarchical multi-
agent architecture that can autonomously fork parallel sub-
agents based on task requirements. Furthermore, we design a unified training framework that linearizes multi-
agent trajectories and optimizes the system using end-to-end RL. Experimental results demonstrate the effectiveness of WideSeek and multi-
agent RL, highlighting that scaling the number of
agents is a promising direction for advancing the Wide Research paradigm.
Read the full abstract ▾
All authors Ziyang Huang, Haolin Ren, Xiaowei Yuan, Jiawei Wang, Zhongtao Jiang, Kun Xu, Shizhu He, Jun Zhao, Kang Liu
Computation and Language
Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management
Siyu Li, Chenwei Song, Qi Zhou et al. (+2 more)
This paper proposes a graph-augmented
reasoning framework for tobacco pest and disease management that integrates structured domain knowledge into large
language models. Building on GraphRAG, we construct a domain-specific knowledge graph and retrieve query-relevant subgraphs to provide relational evidence during answer generation. The framework adopts ChatGLM as the
Transformer backbone with LoRA-based parameter-efficient fine-tuning, and employs a graph neural network to learn node representations that capture symptom-disease-treatment dependencies. By explicitly modeling diseases, symptoms, pesticides, and control measures as linked entities, the system supports evidence-aware
retrieval beyond surface-level text similarity. Retrieved graph evidence is incorporated into the LLM input to guide generation toward domain-consistent recommendations and to mitigate hallucinated or inappropriate treatments. Experimental results show consistent improvements over text-only baselines, with the largest gains observed on multi-hop and comparative
reasoning questions that require chaining multiple relations.
Read the full abstract ▾
All authors Siyu Li, Chenwei Song, Qi Zhou, Wan Zhou, Xinyi Liu
Computation and Language · Cross-listed from cs.NE
Fine-Tuning Language Models to Know What They Know
Sangjun Park, Elliot Meyerson, Xin Qiu et al. (+1 more)
Evaluating true metacognition in Large
Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using the $d'_{\rm type2}$ metric is established to isolate metacognitive ability. The
Evolution Strategy for Metacognitive
Alignment (ESMA) is proposed, demonstrating robust generalization across unseen
datasets,
languages, and newly acquired knowledge. Finally, parameter analysis reveals that these improvements are driven by a sparse set of parameters, offering new pathways for targeted metacognitive optimization.
Read the full abstract ▾
All authors Sangjun Park, Elliot Meyerson, Xin Qiu, Risto Miikkulainen
Computation and Language
Reward-free Alignment for Conflicting Objectives
Peter Chen, Xiaopeng Li, Xi Chen et al. (+1 more)
Direct
alignment methods are increasingly used to align large
language models (LLMs) with human preferences. However, many real-world
alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can lead to unstable training and poor trade-offs. In particular, weighted loss methods may fail to identify update directions that simultaneously improve all objectives, and existing multi-objective approaches often rely on explicit reward models, introducing additional complexity and distorting user-specified preferences. The contributions of this paper are two-fold. First, we propose a Reward-free
Alignment framework for Conflicted Objectives (RACO) that directly leverages pairwise preference data and resolves gradient conflicts via a novel clipped variant of conflict-averse gradient descent. We provide convergence guarantees to Pareto-critical points that respect user-specified objective weights, and further show that clipping can strictly improve convergence rate in the two-objective setting. Second, we improve our method using some heuristics and conduct experiments to demonstrate the compatibility of the proposed framework for LLM
alignment. Both qualitative and quantitative evaluations on multi-objective summarization and safety
alignment tasks across multiple LLM families (Qwen 3, Llama 3, Gemma 3) show that our method consistently achieves better Pareto trade-offs compared to existing multi-objective
alignment baselines.
Read the full abstract ▾
All authors Peter Chen, Xiaopeng Li, Xi Chen, Tianyi Lin
Computation and Language · Cross-listed from cs.LG
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Yinjie Wang, Tianbao Xie, Ke Shen et al. (+2 more)
We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL system for any LLM or agentic scenarios. Specifically, the policy is trained with integrated feedback from step-wise and outcome signals, while the reward model is jointly optimized via consistency feedback, which in turn further improves policy training. Moreover, our theory-motivated automatic environment adaptation improves training for both the reward and policy models by leveraging critic feedback from each, enabling learning from experience. Empirically, each added component consistently improves the overall system, and RLAnything yields substantial gains across various representative LLM and agentic tasks, boosting Qwen3-VL-8B-Thinking by 9.1% on OSWorld and Qwen2.5-7B-Instruct by 18.7% and 11.9% on AlfWorld and LiveBench, respectively. We also that optimized reward-model signals outperform outcomes that rely on human labels. Code: https://github.com/Gen-Verse/Open-AgentRL
Read the full abstract ▾
All authors Yinjie Wang, Tianbao Xie, Ke Shen, Mengdi Wang, Ling Yang
Computation and Language
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
Jialiang Zhu, Gongrui Zhang, Xiaolong Ma et al. (+17 more)
LLM-based deep research
agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often leading to local optima, redundant exploration, and inefficient search. We propose Re-TRAC, an agentic framework that performs cross-trajectory exploration by generating a structured state representation after each trajectory to summarize evidence, uncertainties, failures, and future plans, and conditioning subsequent trajectories on this state representation. This enables iterative reflection and globally informed planning, reframing research as a progressive process. Empirical results show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs. For smaller models, we introduce Re-TRAC-aware supervised fine-tuning, achieving state-of-the-art performance at comparable scales. Notably, Re-TRAC shows a monotonic reduction in tool calls and
token usage across rounds, indicating progressively targeted exploration driven by cross-trajectory reflection rather than redundant search.
Read the full abstract ▾
All authors Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Ruichun Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo
Computation and Language
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
Xiao Liang, Zhong-Zhi Li, Zhenghao Lin et al. (+7 more)
Large
language models (LLMs) have demonstrated strong
reasoning capabilities through step-by-step chain-of-thought (CoT)
reasoning. Nevertheless, at the limits of model capability, CoT often proves insufficient, and its strictly sequential nature constrains test-time scalability. A potential alternative is divide-and-conquer (DAC)
reasoning, which decomposes a complex problem into subproblems to facilitate more effective exploration of the solution. Although promising, our analysis reveals a fundamental misalignment between general-purpose post-training and DAC-style inference, which limits the model's capacity to fully leverage this potential. To bridge this gap and fully unlock LLMs'
reasoning capabilities on the most challenging tasks, we propose an end-to-end reinforcement learning (RL) framework to enhance their DAC-style
reasoning capacity. At each step, the policy decomposes a problem into a group of subproblems, solves them sequentially, and addresses the original one conditioned on the subproblem solutions, with both decomposition and solution integrated into RL training. Under comparable training, our DAC-style framework endows the model with a higher performance ceiling and stronger test-time scalability, surpassing CoT by 8.6% in Pass@1 and 6.3% in Pass@32 on competition-level
benchmarks.
Read the full abstract ▾
All authors Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hancheng Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen
Computation and Language
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Haozhen Zhang, Quanyu Long, Jianzhu Bao et al. (+4 more)
Most Large
Language Model (LLM)
agent memory systems rely on a small set of static, hand-designed operations for extracting
memory. These fixed procedures hard-code human priors about what to store and how to revise
memory, making them rigid under diverse interaction patterns and inefficient on long histories. To this end, we present MemSkill, which reframes these operations as learnable and evolvable
memory skills, structured and reusable routines for extracting, consolidating, and
pruning information from interaction traces. Inspired by the design philosophy of
agent skills, MemSkill employs a controller that learns to select a small set of relevant skills, paired with an LLM-based executor that produces skill-guided
memories. Beyond learning skill selection, MemSkill introduces a designer that periodically reviews hard cases where selected skills yield incorrect or incomplete
memories, and evolves the skill set by proposing refinements and new skills. Together, MemSkill forms a closed-loop procedure that improves both the skill-selection policy and the skill set itself. Experiments on LoCoMo, LongMemEval, HotpotQA, and ALFWorld demonstrate that MemSkill improves task performance over strong baselines and generalizes well across settings. Further analyses shed light on how skills evolve, offering insights toward more adaptive, self-evolving
memory management for LLM
agents.
Read the full abstract ▾
All authors Haozhen Zhang, Quanyu Long, Jianzhu Bao, Tao Feng, Weizhi Zhang, Haodong Yue, Wenya Wang
Computation and Language · Cross-listed from cs.LG
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
Qifan Yu, Xinyu Ma, Zhijian Zhuo et al. (+7 more)
Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansion remains significantly understudied, with the few existing methods limited to the early stages of training. However, expanding width during the mid-stage is essential for maximizing computational savings, yet it remains a formidable challenge due to severe training instabilities. Empirically, we show that naive initialization at this stage disrupts activation statistics, triggering loss spikes, while copy-based initialization introduces gradient
symmetry that hinders feature diversity. To address these issues, we propose SPARKLING (balancing {S}ignal {P}reservation {A}nd symmet{R}y brea{K}ing for width-progressive {L}earn{ING}), a novel framework for mid-stage width expansion. Our method achieves signal preservation via RMS-scale consistency, stabilizing activation statistics during expansion.
Symmetry breaking is ensured through asymmetric optimizer state reset and asymmetric learning rate re-warmup. Extensive experiments on dense and Mixture-of-Experts (MoE) models demonstrate that, across multiple width axes and optimizer families, SPARKLING consistently outperforms training from scratch and reduces training cost by up to 35% under $2\times$ width expansion.
Read the full abstract ▾
All authors Qifan Yu, Xinyu Ma, Zhijian Zhuo, Minrui Wang, Deyi Liu, Shiyi Zhan, Yiyuan Ma, Liang Xiang, Xingyan Bin, Di He
Computation and Language · Cross-listed from cs.AI
Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts
Aiden Yiliu Li, Xinyue Hao, Shilong Liu et al. (+1 more)
Despite advances in
multimodal large
language models, autonomous web
agents still struggle to reliably execute long-horizon tasks on complex and dynamic web interfaces. Existing
agents often suffer from inaccurate element grounding, the absence of site-specific procedural knowledge, and unstable long-term task tracking and
memory, particularly when operating over complex Document Object Model structures. To address these limitations, we introduce Avenir-Web, a web
agent that achieves a new open-source state of the art on the Online-Mind2Web
benchmark in real-world deployment. Avenir-Web leverages a Mixture of Grounding Experts, Experience-Imitation Planning for incorporating procedural priors, and a task-tracking checklist combined with adaptive
memory to enable robust and seamless interaction across diverse user interface paradigms. We evaluate Avenir-Web on Online-Mind2Web, a rigorous
benchmark of live and user-centered web tasks. Our results demonstrate that Avenir-Web significantly surpasses prior open-source
agents and attains performance parity with top-tier proprietary models, thereby establishing a new open-source state of the art for reliable web
agents on live websites.
Read the full abstract ▾
All authors Aiden Yiliu Li, Xinyue Hao, Shilong Liu, Mengdi Wang
Computation and Language
Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
Noam Steinmetz Yalon, Ariel Goldstein, Liad Mudrik et al. (+1 more)
Rapid advancements in large
language models (LLMs) have sparked the question whether these models possess some form of consciousness. To tackle this challenge, Butlin et al. (2023) introduced a list of indicators for consciousness in artificial systems based on neuroscientific theories. In this work, we evaluate a key indicator from this list, called HOT-3, which tests for agency guided by a general belief-formation and action selection system that updates beliefs based on meta-cognitive monitoring. We view beliefs as representations in the model's latent space that emerge in response to a given input, and introduce a metric to quantify their dominance during generation. Analyzing the dynamics between competing beliefs across models and tasks reveals three key findings: (1) external manipulations systematically modulate internal belief formation, (2) belief formation causally drives the model's action selection, and (3) models can monitor and report their own belief states. Together, these results provide empirical support for the existence of belief-guided agency and meta-cognitive monitoring in LLMs. More broadly, our work lays methodological groundwork for investigating the emergence of agency, beliefs, and meta-cognition in LLMs.
Read the full abstract ▾
All authors Noam Steinmetz Yalon, Ariel Goldstein, Liad Mudrik, Mor Geva
Computation and Language
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
Or Shafran, Shaked Ronen, Omri Fahn et al. (+3 more)
Activation decomposition methods in
language models are tightly coupled to
geometric assumptions on how concepts are realized in activation space. Existing approaches search for individual global directions, implicitly assuming linear separability, which overlooks concepts with nonlinear or multi-dimensional structure. In this work, we leverage Mixture of Factor Analyzers (MFA) as a scalable, unsupervised alternative that models the activation space as a collection of Gaussian regions with their local covariance structure. MFA decomposes activations into two compositional
geometric objects: the region's centroid in activation space, and the local variation from the centroid. We train large-scale MFAs for Llama-3.1-8B and Gemma-2-2B, and show they capture complex, nonlinear structures in activation space. Moreover, evaluations on localization and steering
benchmarks show that MFA outperforms unsupervised baselines, is competitive with supervised localization methods, and often achieves stronger steering performance than sparse autoencoders. Together, our findings position local geometry, expressed through subspaces, as a promising unit of analysis for scalable concept discovery and model control, accounting for complex structures that isolated directions fail to capture.
Read the full abstract ▾
All authors Or Shafran, Shaked Ronen, Omri Fahn, Shauli Ravfogel, Atticus Geiger, Mor Geva
Computation and Language
Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto et al. (+1 more)
Large
Language Models (LLMs) often struggle with deductive judgment in syllogistic
reasoning, systematically conflating semantic plausibility with formal validity a phenomenon known as content effect. This bias persists even when models generate step-wise explanations, indicating that intermediate rationales may inherit the same semantic shortcuts that affect answers. Recent approaches propose mitigating this issue by increasing inference-time structural constraints, either by encouraging abstract intermediate representations or by intervening directly in the model's internal computations; however, reliably suppressing semantic interference remains an open challenge. To make formal deduction less sensitive to semantic content, we introduce a framework for abstraction-guided
reasoning that explicitly separates structural inference from lexical semantics. We construct paired content-laden and abstract syllogisms and use the model's activations on abstract inputs to define an abstract
reasoning space. We then learn lightweight Abstractors that, from content-conditioned residual-stream states, predict representations aligned with this space and integrate these predictions via multi-layer interventions during the forward pass. Using cross-lingual transfer as a test bed, we show that abstraction-aligned steering reduces content-driven errors and improves validity-sensitive performance. Our results position activation-level abstraction as a scalable mechanism for enhancing the robustness of formal
reasoning in LLMs against semantic interference.
Read the full abstract ▾
All authors Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto, Leonardo Ranaldi
Computation and Language · Cross-listed from cs.AI
Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
Han Bao, Zheyuan Zhang, Pengcheng Jing et al. (+3 more)
As Large
Language Models transition to autonomous
agents, user inputs frequently violate cooperative assumptions (e.g., implicit intent, missing parameters, false presuppositions, or ambiguous expressions), creating execution risks that text-only evaluations do not capture. Existing
benchmarks typically assume well-specified instructions or restrict evaluation to text-only, single-turn clarification, and thus do not measure multi-turn disambiguation under grounded execution risk. We introduce Drift-Bench, the first diagnostic
benchmark that evaluates agentic pragmatics under input faults through multi-turn clarification across state-oriented and service-oriented execution environments. Grounded in classical theories of communication, Drift-Bench provides a unified taxonomy of cooperative breakdowns and employs a persona-driven user simulator with the Rise evaluation protocol. Experiments show substantial performance drops under these faults, with clarification effectiveness varying across user personas and fault types. \MethodName bridges clarification research and
agent safety evaluation, enabling systematic diagnosis of failures that can lead to unsafe executions.
Read the full abstract ▾
All authors Han Bao, Zheyuan Zhang, Pengcheng Jing, Zhengqing Yuan, Kaiwen Shi, Yanfang Ye
Computation and Language
Large Language Models for Mental Health: A Multilingual Evaluation
Nishat Raihan, Sadiya Sayara Chowdhury Puspo, Ana-Maria Bucur et al. (+2 more)
Large
Language Models (LLMs) have remarkable capabilities across NLP tasks. However, their performance in
multilingual contexts, especially within the mental health domain, has not been thoroughly explored. In this paper, we evaluate proprietary and open-source LLMs on eight mental health
datasets in various
languages, as well as their machine-translated (MT) counterparts. We compare LLM performance in zero-shot, few-shot, and fine-tuned settings against conventional NLP baselines that do not employ LLMs. In addition, we assess translation quality across
language families and typologies to understand its influence on LLM performance. Proprietary LLMs and fine-tuned open-source LLMs achieve competitive F1 scores on several
datasets, often surpassing state-of-the-art results. However, performance on MT data is generally lower, and the extent of this decline varies by
language and typology. This variation highlights both the strengths of LLMs in handling mental health tasks in
languages other than English and their limitations when translation quality introduces structural or lexical mismatches.
Read the full abstract ▾
All authors Nishat Raihan, Sadiya Sayara Chowdhury Puspo, Ana-Maria Bucur, Stevie Chancellor, Marcos Zampieri
Computation and Language
Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank
Joshua Mitton, Prarthana Bhattacharyya, Digory Smith et al. (+3 more)
Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly dependent on the effort and intuition of the teacher. In this work, we present a novel approach for detecting misconceptions from student-tutor dialogues using large
language models (LLMs). First, we use a fine-tuned LLM to generate plausible misconceptions, and then retrieve the most promising candidates among these using
embedding similarity with the input dialogue. These candidates are then assessed and re-ranked by another fine-tuned LLM to improve misconception relevance. Empirically, we evaluate our system on real dialogues from an educational tutoring platform. We consider multiple base LLM models including LLaMA, Qwen and Claude on zero-shot and fine-tuned settings. We find that our approach improves predictive performance over baseline models and that fine-tuning improves both generated misconception quality and can outperform larger closed-source models. Finally, we conduct ablation studies to both validate the importance of our generation and reranking steps on misconception generation quality.
Read the full abstract ▾
All authors Joshua Mitton, Prarthana Bhattacharyya, Digory Smith, Thomas Christie, Ralph Abboud, Simon Woodhead
Computation and Language
ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs
Ziyan Zhang, Chao Wang, Zhuo Chen et al. (+2 more)
Answering first-order logic (FOL) queries over incomplete knowledge graphs (KGs) is difficult, especially for complex query structures that compose projection, intersection, union, and negation. We propose ROG, a
retrieval-augmented framework that combines query-aware neighborhood
retrieval with large
language model (LLM) chain-of-thought
reasoning. ROG decomposes a multi-operator query into a sequence of single-operator sub-queries and grounds each step in compact, query-relevant neighborhood evidence. Intermediate answer sets are cached and reused across steps, improving consistency on deep
reasoning chains. This design reduces compounding errors and yields more robust inference on complex and negation-heavy queries. Overall, ROG provides a practical alternative to
embedding-based logical
reasoning by replacing learned operators with
retrieval-grounded, step-wise inference. Experiments on standard KG
reasoning benchmarks show consistent gains over strong
embedding-based baselines, with the largest improvements on high-complexity and negation-heavy query types.
Read the full abstract ▾
All authors Ziyan Zhang, Chao Wang, Zhuo Chen, Chiyi Li, Kai Song
Computation and Language
From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making
Raunak Jain
As LLMs expand from assistance to decision support, a dangerous pattern emerges: fluent agreement without calibrated judgment. Low-friction assistants can become sycophantic, baking in implicit assumptions and pushing verification costs onto experts, while outcomes arrive too late to serve as reward signals. In deep-uncertainty decisions (where objectives are contested and reversals are costly), scaling fluent agreement amplifies poor commitments faster than it builds expertise. We argue reliable human-AI partnership requires a shift from answer generation to collaborative premise governance over a knowledge substrate, negotiating only what is decision-critical. A discrepancy-driven control loop operates over this substrate: detecting conflicts, localizing misalignment via typed discrepancies (teleological, epistemic, procedural), and triggering bounded negotiation through decision slices. Commitment gating blocks action on uncommitted load-bearing premises unless overridden under logged risk; value-gated challenge allocates probing under interaction cost. Trust then attaches to auditable premises and evidence standards, not conversational fluency. We illustrate with tutoring and propose falsifiable evaluation criteria.
Read the full abstract ▾
Computation and Language
ProofVerifier: A Scalable, Diversity-Driven Framework for Natural-Language Proof Verification
Haotong Yang, Zitong Wang, Shijia Kang et al. (+7 more)
While large
language models (LLMs) have achieved strong performance on mathematical problems with verifiable answers, many advanced problems are proof-based and require evaluating full proofs. However, training such verifiers requires diverse and trustworthy question-proof-check (QPC) examples at scale, which are scarce. To address this challenge, we develop a human-audited, LLM-assisted data pipeline that produces large-scale QPC triplets with limited human effort. By systematically varying problem sources, generation strategies, and generator models, the pipeline creates diverse problem-proof pairs spanning multiple difficulty levels, linguistic styles, and error types. We combine multi-LLM agreement with hierarchical human
auditing to obtain accurate proof-correctness labels. Using these data, we train generative proof verifiers and introduce an auxiliary fluency filter together with balanced
token weighting to stabilize binary-reward long-form verification RL. Experiments show that our verifier improves proof-judgment accuracy across different proof styles and provides useful guidance for test-time selection. Overall, our results provide a practical data and training framework for natural-
language proof verification.
Read the full abstract ▾
All authors Haotong Yang, Zitong Wang, Shijia Kang, Siqi Yang, Wenkai Yu, Xu Niu, Yike Sun, Yi Hu, Zhouchen Lin, Muhan Zhang
Computation and Language
Automated Multiple Mini Interview (MMI) Scoring
Ryan Huynh, Frank Guerin and Alison Callwood
Assessing soft skills such as empathy, ethical judgment, and communication is essential in competitive selection processes, yet human scoring is often inconsistent and biased. While Large
Language Models (LLMs) have improved Automated Essay Scoring (AES), we show that state-of-the-art rationale-based fine-tuning methods struggle with the abstract, context-dependent nature of Multiple Mini-Interviews (MMIs), missing the implicit signals embedded in candidate narratives. We introduce a multi-
agent prompting framework that breaks down the evaluation process into transcript refinement and criterion-specific scoring. Using 3-shot in-context learning with a large instruct-tuned model, our approach outperforms specialised fine-tuned baselines (Avg QWK 0.62 vs 0.32) and achieves reliability comparable to human experts. We further demonstrate the generalisability of our framework on the ASAP
benchmark, where it rivals domain-specific state-of-the-art models without additional training. These findings suggest that for complex, subjective
reasoning tasks, structured
prompt engineering may offer a scalable alternative to data-intensive fine-tuning, altering how LLMs can be applied to automated assessment.
Read the full abstract ▾
Computation and Language
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu, Chenyan Wu, Hengyu Sun et al. (+9 more)
Methods for controlling large
language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames these interventions as dynamic weight updates induced by a control signal, placing them within a single conceptual framework. Building on this view, we propose a unified preference-utility analysis that separates control effects into preference, defined as the tendency toward a target concept, and utility, defined as coherent and task-valid generation, and measures both on a shared log-odds scale using polarity-paired contrastive examples. Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility. We further explain this behavior through an activation
manifold perspective, in which control shifts representations along target-concept directions to enhance preference, while utility declines primarily when interventions push representations off the model's valid-generation
manifold. Finally, we introduce a new steering approach SPLIT guided by this analysis that improves preference while better preserving utility. Code is available at https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md.
Read the full abstract ▾
All authors Ziwen Xu, Chenyan Wu, Hengyu Sun, Haiwen Hong, Mengru Wang, Yunzhi Yao, Longtao Huang, Hui Xue, Shumin Deng, Zhixuan Chu, Huajun Chen, Ningyu Zhang
Computation and Language
Neeraja Kirtane and Kuan-Hao Huang
If
multilingual language model representations contain separable
language-associated structure, then shifting between
languages may require only simple activation-space interventions. To test this hypothesis, we study
multilingual in-context learning (ICL) as a controlled setting: few-shot demonstrations are provided in English while the test query is in a target
language, creating a clear cross-lingual transfer challenge. We propose
language vectors, which are computed as mean activation differences between parallel source and target
language examples at a particular layer and applied as inference-time offsets to the model's hidden states. Across three tasks spanning 19
languages and three models, our method improves over English few-shot prompting without any parameter updates. Beyond performance, the vectors encode interpretable linguistic structure: closely related
languages form tight clusters, and vectors transfer effectively across tasks and
languages, with closely related
languages' vectors recovering more of the gain than distant ones. Together, these findings suggest that
language occupies structured directions in
multilingual activation space, and that inference-time interventions on English demonstrations can narrow the cross-lingual ICL gap.
Read the full abstract ▾