paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution

Ting Wei Li, Yuanchen Bei, Xiao Lin, Hanghang Tong

Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task of Agent Failure Attribution: given a failed multi-agent trajectory, identify the faulty agents and their corresponding error types. Existing approaches predominantly rely on LLMs to perform failure attribution, either through direct prompting, fine-tuning on synthetic data or complex agentic pipelines. While effective, these methods incur substantial computational overhead due to long-context processing, expensive post-training and handcrafted workflows. Moreover, empirical evidence shows that even state-of-the-art models achieve limited accuracy on existing benchmarks, suggesting that scaling model size alone is insufficient. In this work, we revisit this task and question the necessity of such expensive generative solutions. We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships. We show that with significantly fewer parameters and near-zero inference cost, AFANet (i) matches or outperforms LLM-based baselines, including fine-tuned models on in-domain benchmarks, (ii) maintains robust performance across different GNN architectures and (iii) can be further improved with inexpensive test-time adaptation on the OOD benchmark. Our results suggest that effective agent failure attribution does not require heavy LLM reasoning and a lightweight, structured approach can achieve strong performance.

arXiv

Shared Circuits for Shared Grammar: Tracing Subject-Verb Agreement Across Languages

Isabella Gidi, Antonio Almudévar, Core Francisco Park, Naomi Saphra, Ricard Marxer

Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually. It remains unclear, however, when such sharing emerges and whether it varies with the overt realization of the same grammatical operation. We investigate this question for present-tense subject-verb agreement, a morphosyntactic process that varies substantially across languages and is only weakly expressed in English. Using activation patching and attention analysis across 29 languages and five open-source model families, we identify the attention heads causally implicated in agreement and compare these head-level signatures across languages. We find that languages with overt person/number inflection exhibit more similar agreement circuitry than non-conjugating languages, with the strongest sharing appearing when the analysis isolates recovery of the inflectional contrast itself. English provides an informative bridge case, becoming more similar to conjugating languages precisely in contexts where overt agreement is required. Finally, many implicated heads display similar attention patterns across languages, suggesting that cross-lingual overlap reflects shared functional roles as well as shared localization. Together, these results indicate that multilingual LLMs reuse partially shared computational structure for morphosyntactic agreement rather than relying on fully separate language-specific solutions.

arXiv

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu, Fangda Chen, Ziqi Wu, Jingming Cai, Yan Song

Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse, indiscriminately penalizing valid alternative explorations and severely degrading policy diversity. To address this, we propose DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction. DART-SD first models the execution process as a converging Interaction-State Transition Graph (ISTG), faithfully capturing the inherent diamond topology of successful and failed exploratory paths. During autonomous rollouts, the framework identifies the Critical Topological Breakpoint (CTB) and retrieves success-supported recovery references. Finally, we introduce a progressive self-distillation paradigm through CTB-guided localized supervision, ensuring that the training loss is calculated exclusively on the generated recovery steps while strictly protecting the valid reasoning prefix from destructive gradient updates. Experiments on complex multi-turn tool-calling benchmarks demonstrate that DART-SD significantly outperforms traditional full-trajectory baselines.

arXiv

MissDiag: Diagnostic Evaluation of Incomplete-Knowledge Robustness in KGQA and KG-RAG

Hang Wang, Hang Dong, Lu Liu, Chuanru Ren

Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evidence, but real-world knowledge graphs are often sparse, outdated, and incomplete. Existing robustness evaluations usually report aggregate changes in answer quality after evidence is removed or perturbed, which measures sensitivity to incomplete support but leaves the source of degradation under-specified: the same score change can conflate the type of missing evidence, the response of the evaluated system, and the sensitivity of the answer-matching protocol. To address this gap, we propose \textbf{MissDiag}, a diagnostic evaluation framework for incomplete-knowledge robustness in KGQA and KG-RAG. MissDiag keeps the question and gold answer fixed while applying structurally typed missingness interventions to benchmark-provided support graphs, enabling paired comparisons that decompose robustness changes by evidence type, system response, and evaluation protocol rather than reducing them to a single aggregate score drop. Experiments across multiple system families show that incomplete-knowledge robustness is better understood as a typed degradation phenomenon than as a uniform property: answer-adjacent evidence loss produces the largest observed degradation, source-context removal is often neutral and can be beneficial, and semantic answer matching changes absolute scores while preserving the main typed degradation patterns. By transforming aggregate robustness measurement into typed diagnostic attribution, MissDiag provides a more interpretable basis for comparing, diagnosing, and stress-testing KGQA and KG-RAG systems under incomplete knowledge.

arXiv

WhiteMatter: All-to-All Cross-Layer Connections via KV Mixing

Wenbo Zhang, Xiang Ren

In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during autoregressive decoding. Feedback architectures allow shallow consumer layers to attend to KV produced by deeper past-token representations, but give all consumer layers the same fixed connection patterns to source layers. We propose WhiteMatter, which connects every attention layer to the representations from all layers of each past token, with connection weights that can vary across consumer layers and adapt to the source token. For each token, a router implements these connections by mixing its $L$ layer states into $k$ KV channels that are cached for subsequent tokens; each consumer layer attends to one of the channels. The number of channels $k$ controls the KV-cache size. Setting $k<L$ reduces the cache's memory footprint. In our pretraining experiments, WhiteMatter outperforms a vanilla Transformer with 50% more layers and retains most of this gain with a 50% KV-cache compression.

arXiv

Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines

Eduardo de Conto, Blaise Genest, Arvind Easwaran, Nicholas Ng, Shweta Menon

Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines, both to build real-time DTs from high-fidelity simulations and to instantiate them with historical data. However, engineering these pipelines remains largely ad-hoc: pipelines are hard to specify, validate, and reuse, with scarce dedicated tooling. Function+Data Flow (FDF) addresses this by defining a visual domain-specific language (DSL) that represents functions (ML models) explicitly, enabling their composition and reuse. We implemented FDF in DesCartes Builder, an integrated modeling environment supporting FDF-based DT synthesis and validation. In this paper, we report on an empirical user study evaluating whether FDF and DesCartes Builder can make AI-based DT development more accessible and reliable. Participants implemented a representative real-time DT prototype within DesCartes Builder, and we measured perceived usability and feature adequacy through quantitative and qualitative measures. Our results indicate that DesCartes Builder and FDF achieve a good level of usability across a broad range of potential users, and particularly for the intended audience of domain experts. The study additionally surfaces concrete strengths and areas for improvement of both the tool and the underlying FDF framework. Informed by these findings, we propose H-FDF, a Hierarchical extension of FDF supporting iterative and modular pipelines, enabling the formal specification of more complex DT pipelines such as dual training. Our findings suggest that integrated, model-driven platforms are a promising direction to transform AI-based DT engineering into a disciplined modeling practice.

arXiv

OmniAlign: A Unified Multilingual Aligner for Word and Sentence Alignment

Mengpeng Yang, Jingxu Yang, Chao Chen, Tian Xia, Yabo Sun, Qiang Liu

Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords. Existing tools, however, typically specialize in a single granularity, so practitioners often need separate systems for word- and sentence-level alignment---especially in multilingual and long-text settings. We present OmniAlign, a unified multilingual aligner that supports both word-level and sentence-level alignment with a single lightweight model. Built on an encoder-only backbone with strong long-context modeling, OmniAlign induces word alignments from contextualized token similarity matrices, and obtains document-level $m$--$n$ sentence alignments via sentence embeddings combined with dynamic programming. To balance fine-grained alignment accuracy and sentence-representation quality, we use a four-stage training pipeline: alignment-oriented continued pre-training, self-supervised learning, supervised fine-tuning on human annotations, and sentence-embedding distillation from a strong multilingual teacher. Experiments show that OmniAlign achieves highly competitive performance on both word- and sentence-alignment benchmarks and generalizes well to unseen language pairs. Surprisingly, later-stage supervised fine-tuning on short texts further improves alignment quality while retaining the long-context understanding acquired in earlier training, keeping the model robust on long-text word alignment. \normalsize {\color{blue}\textbf{Code}: https://github.com/MilkDargon/OmniAlign}\par {\color{blue}\textbf{Model}: https://huggingface.co/WPS-Qingqiu/OmniAlign}

arXiv

More Context, Same Budget: Dual-Bounded Relational Recall Beyond Top-K Retrieval

Thomson D. Nguy

More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requires by following relationships between evidence that flat top-k ranking leaves behind. We test that proposition with Dual-Bounded Relational Recall (DBRR), which allocates a fixed retrieval budget between relevance-selected seeds and bounded graph-adjacent context, against matched flat top-k retrieval using the same relevance-ranking stage and the same maximum number of retrieval units and tokens. The outcome is complete recovery of the official HotpotQA supporting-evidence set for each question. Across 7,405 FullWiki questions, the Primary DBRR allocation increased complete supporting-evidence recovery by 23.8 percentage points over its matched flat baseline (paired risk difference 0.2377; question-level bootstrap 95% interval 0.2269 to 0.2489). It improved 1,952 questions, tied on 5,261, and harmed 192. Bridge questions drove the effect, with a 28.7-point increase; comparison questions showed a smaller 4.2-point difference. In a prespecified, evaluation-only diagnostic population, real relationships also outperformed random-neighbor and degree-preserving shuffled-graph controls. The result is straightforward: under the same context budget, complete-evidence retrieval depends not only on which items rank highest, but on how context is allocated around them. Relational allocation recovered complete evidence sets that flat top-k retrieval left incomplete.

arXiv

Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage

Shreeya Sharma, Ravish Gupta, Saket Kumar, Abhishek Aggarwal

Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a "supervision gap" where novice therapists manage high-stakes risks with delayed professional feedback. This paper proposes a new framework utilizing a fine-tuned Mistral-7B-instruct model as an automated "Supervisor-in-the-Loop" system. By leveraging 106 sessions from the DAIC-WOZ dataset, the model performs a tri-stream analysis: (1) Therapeutic Alliance tracking via semantic adherence, (2) Latent risk prediction using attention-weighted analytics, and (3) Supervisory Triage via a Dynamic Clinical Urgency Index (D-CUI). Our multi-modal VAL (Visual-Acoustic-Linguistic) framework achieves 95% technique identification accuracy [95% CI: 75.1%-99.9%], alliance assessment MAE of 0.105 on a 5-point scale [95% CI: 0.059-0.151], therapeutic fidelity alpha = 0.423, and mean D-CUI of 0.370 [95% CI: 0.322-0.419]. Training converged in 105 steps with 85.2% loss reduction on a single Tesla T4 GPU. The system reduces supervisory triage latency from 72 hours to real time (~10 seconds per session), enabling proactive intervention in high-risk cases. The system addresses the cold-start problem through Bayesian priors and implements timestamp-based modality synchronization for robust multi-modal fusion.

arXiv

Tangut Word Segmentation under Extreme Resource Scarcity: Integrating Traditional Lexicons and Unlabeled Text

Lifan Deng, Yongwei Zhang, Sen Sun, Bojun Sun, Jingsong Yu

Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation using 2,750 expert-annotated segments(31,893 tokens), traditional lexicons, and unlabeled text. Our framework combines a reliability-calibrated lexicon-lattice representation, explicit distributional statistics, and a lightweight character encoder pretrained with MLM. Segment-level five-fold cross-validation shows that lexical and statistical features raise CRF F1 to approximately 0.91. The full TangutEncoder reaches the highest mean F1 (0.911) and improves recall beyond the labeled training vocabulary. These results demonstrate generalization beyond the limited supervised vocabulary across thematically diverse held-out passages, while document-level transfer remains to be evaluated.

arXiv

Multimodal Rapport Estimation in Real-World HRI

Akihiro Sakuramoto, Takato Hayashi, Ryo Miyoshi, Yuki Okafuji, Shogo Okada

Evaluating interaction quality in real-world HRI is an important challenge. If interaction quality can be estimated reliably, the results can be used to improve dialogue strategies and ultimately enable robots to adapt their behavior autonomously. However, existing automatic evaluation methods have been developed primarily in controlled laboratory settings, and it remains unclear whether they can be directly applied to real-world environments, where users are free to disengage and multi-party participation may arise naturally. In this study, we investigate the automatic estimation of third-party-rated rapport scores using 62 sessions of multimodal recordings collected in a Japanese drugstore. We compare zero-shot LLMs, pretrained text, audio, and visual models, and their prediction-level fusion. The results show that, in real-world HRI, zero-shot LLMs achieve strong performance, while audio and visual models tend to provide complementary information. In particular, Gemini 2.5 Flash performs strongly as a single model, and a fusion model combining Gemini (text) with HuBERT and V-JEPA performs best overall. Further analyses showed that estimation performance varied across interaction-duration and group-size conditions. These findings suggest that rapport estimation in real-world HRI requires evaluation and model design that account for contextual variability beyond that assumed in laboratory settings.

arXiv

Cross-Model Memory Transfer via Target-Side Reader Adaptation

Mingyuan Li, Guangsheng Yu, Xu Wang, Shaoxiong Ji

Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but adds retrieval latency, context overhead, and only shallow integration with the backbone. Parametric adaptation is efficient at inference time, but entangles knowledge with model weights and can be hard to update, audit, or transfer. Engram-style hashed memory occupies a middle regime: it stores learned information in an external, addressable table, yet consumes that table through a small learned reader. This raises a basic question: when such a memory is moved across backbones, what matters more, the frozen memory itself or the target-side reader? We study this question through cross-model frozen-memory extraction, in which a memory trained on a source model is frozen and attached to a different target model, with only a lightweight reader trained. Ablations show that learned memory content and correct addressing both matter, but the transferred table becomes useful only through a reader aligned to the target model. In downstream question answering tasks, a dual-layer, four-branch reader nearly closes the gap between same-model and cross-model reuse, achieving an average score of 38.8 under our controlled evaluation protocol. Moreover, when the provider reader is directly compatible with the target interface, the frozen artifact can provide substantial utility without target-side training, while optional reader adaptation yields further improvement. These results suggest that Engram can serve as a reusable external knowledge artifact, provided that the target has access to a compatible reader interface; target-side adaptation can further improve alignment when direct reader reuse is insufficient.

arXiv

SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior Feedback

Yuxin Du, Juxin Niu, Tao Hu, Xi Wang, Zhe jiang, Nan Guan

RTL code generation is a critical stage in hardware design, and the emergence of agentic systems offers new opportunities to automate this process. To generate correct RTL code, agents must understand sequential behavior, including how signals evolve and propagate over multiple clock cycles. However, effectively conveying such temporal information to agents remains a significant challenge. RTL code does not expose cycle-level signal behavior for a specific execution, whereas full simulation waveforms are too voluminous and noisy for effective LLM analysis. To address these limitations, we study how human engineers reason about sequential behavior and identify three requirements for effective feedback: it should be event-addressable, dependency-traceable, and iteratively-queryable. Guided by these requirements, we propose \textit{SeqFeed}, which comprises two complementary mechanisms: (1) \textit{SeQuery}, an SQL-like waveform query language that enables agents to anchor queries to semantic events and sample signal values at relative time points; and (2) \textit{SeGraph}, a dependency graph that tracks signal propagation across clock cycles. Experimental results across multiple LLMs demonstrate the effectiveness of SeqFeed in improving pass rates. SeQuery and SeGraph are each effective independently and provide complementary benefits when used together.

arXiv

Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

Shaolong Chen, Yanlin Fei, Nazhou Liu, Xinmiao Yu, Lei Li, Rahul Thapa, Madalina Ciobanu, Navan Preet Singh, Qingqing Mao, Ritankar Das

Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recovery benchmark that withholds the seed paper and all contemporaneous or future literature, and asks models to propose hypotheses that an independent large language model judge matches against the held-out ground-truth idea. A strict anti-leakage protocol-temporal citation cutoff, anonymous reference IDs, and frozen per-paper bibliographies, which prevents prompt-time leakage of the seed idea. Across six scientific domains and 643 evaluated papers, seven frontier models achieve only modest Match rates (approx. 3-15%). We then evaluate a reference-only multi-agent (top 4) pipeline that combines cross-model review with a Swiss tournament over aligned hypothesis slots, without external web search. Cross-model review plus tournament selection raises Match rates to approx. 23-42% across all six domains, which is an observed approx. 2.4x lift over the best single-model baseline. This draft reports the protocol, anti-leakage design, and current results as an arXiv timestamp.

arXiv

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Zhengzhao Ma, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely rely on local signals, such as token probabilities, predictive entropy, or per-step confidence, and therefore overlook the long-range dependencies through which errors accumulate across an execution trajectory. As a result, they may fail to identify agent failures whose causes originate several reasoning or interaction steps before the final answer. We propose RUPA (Relational Uncertainty Propagation for Agents), a trajectory-level UQ framework for LLM agents. RUPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges. It then propagates uncertainty over this graph to capture how execution risk accumulates and transfers across interaction steps. The propagated signal is combined with trajectory-level behavioral features and goal-alignment information to produce a confidence estimate for the full agent trajectory. We evaluate RUPA on representative agent benchmarks, including $τ$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families. Experimental results show that RUPA consistently outperforms existing UQ methods by providing more accurate uncertainty estimates, enabling earlier failure detection, and improving uncertainty-guided agent execution across diverse agent tasks. These results demonstrate that explicitly modeling relational dependency is crucial to reliable UQ for long-horizon LLM agents, providing a practical foundation for trustworthy agent execution.

arXiv

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

Yanlin Fei, Nazhou Liu, Xinmiao Yu, Shaolong Chen, Lei Li, Rahul Thapa, Madalina Ciobanu, Navan Preet Singh, Qingqing Mao, Ritankar Das

AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage research from an initial hypothesis all the way to final published paper, which is a paradigm now referred to as AutoResearch. Existing evaluations reveal little about how these agents operate or where they break down. Tasks are narrowly-scoped, evaluation measures performance but not process, and failure diagnoses lack systematic coverage or artifact-level visibility. To address this gap, we introduce AutoResearchEval, featuring 100 tasks grounded in published frontier science across 7 scientific domains and the full research lifecycle, including ideation, retrieval, execution, analysis, writing, and review. Evaluating 8 harness-model combinations yields 800 autoresearch agent trajectories, with process-level annotation. We organize these insights into AutoResearch Failure Taxonomy or ARFT, a framework of 45 empirically-grounded failure patterns. To enable scalable fine-grained attribution, we leverage a human-calibrated agent-as-a-judge pipeline to inspect complete trajectories and intermediate artifacts. Failure patterns converge on a single overarching limitation, namely that current agents lack a metacognitive loop, which entails the ability to check what they produced against what they found, revise when it does not hold up, and question whether the path they took was sound. The same patterns recur across all 8 harness-model combinations, including the strongest models tested, locating the deficit at the model level rather than in any particular scaffold; whether orchestration-level interventions can close it is an open question this work does not test. We publicly release AutoResearchEval and ARFT to facilitate continued research and development in autonomous scientific discovery.

arXiv

Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors

Lingkai Bu, Qian Gao, Jun Fan, Guohui Ding, Zhenyu Yang, Yuteng Xiao, Jinyi Liang

Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing tying an object mention to the image. Most remedies intervene at decoding time, yet under a unified protocol their benefit is confined to short captions; supervised fine-tuning (SFT) on a detail-rich corpus lengthens captions, but over forty percent still name absent objects. This paper proposes Dual-Stream Cross-Anchor Correction (DSCC). Unlike work that post-processes decoding, DSCC injects object-level visual anchors into the language model itself during fine-tuning: a perception stream aligns object-level hidden states at an intermediate layer to frozen text anchors by a bidirectional contrastive objective; a cognition stream lets deeper layers query those anchors by cross-attention at every generation step; and a two-stage curriculum gate couples them, making evidence retrieval a structural constraint on generation. Under one backbone and one scoring protocol, experiments span long-caption hallucination, object-existence discrimination and cross-domain generalisation, with vanilla SFT on the same corpus and schedule as a length- and density-matched control separating the data effect from the architectural gain. DSCC alone reaches the long-caption, low-hallucination region: captions roughly 1.9 times the baseline length at 88.19% precision per object mention, the highest under a density-independent criterion. Ablations expose a synergy: the perception stream alone degrades precision yet reverses sign when stacked on the cognition stream. No universal superiority is claimed: three out-of-domain benchmarks yield a predictable, falsifiable domain-conditionality, the synergy being bound to the anchors' semantic domain and breaking on charts and illusions.

arXiv

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Zhixiang Cui, Xin Xu, Yunzhi Yao, Buqiang Xu, Fei Shen, Haozhe Luo, Yunxiang Wei, Ningyu Zhang, Julian McAuley, Tat-Seng Chua, Huajun Chen

AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI development becomes faster and increasingly automated, mechanistic exploration remains largely manual, widening the gap between what models can do and our ability to understand and control them. To bridge this gap, we introduce Mechanist, an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence. To support autonomous mechanistic discovery, we construct an interpretability-focused knowledge graph of approximately 13,000 papers and integrate it with a multidisciplinary database of 43 million papers spanning 26 fields. We further curate a library of 32 foundational methods for mechanism analysis, causal intervention, and validation. Compared with Claude Code and existing AI-scientist systems, Mechanist generates more valuable mechanism hypotheses and executes experiments more reliably. Mechanist also demonstrates a progression from discovering model behaviors to explaining and controlling AI models. Specifically, Mechanist first uncovers a counterintuitive safety risk in scientific laboratories, showing that unsafe traits can transfer across modalities through apparently safe training data. Mechanist then develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining. Finally, Mechanist translates these mechanistic insights into practical interventions that improve model performance across diverse scenarios and steer scientific foundation models toward generating DNA sequences with specified properties.

arXiv

X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction

Kaiqi Fu, Rime Wen, Altman Lin, Shawn Qin, Roy Gan, Hao Wang, Qian Wang

Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchannels that should be ignored, and the completion of an utterance. Prior modular approaches typically optimize turn state prediction at the utterance or fixed-chunk level, creating a mismatch with the continuous turn state estimate, and often depend on an auxiliary ASR model, which limits responsiveness and increases overall system complexity. Therefore, we present X2-Turn, a frame-synchronous turn state prediction method via delayed-stream modeling. Specifically, building on the pretrained Voxtral Realtime model, we introduce a frame-synchronous turn state head that operates in parallel with the ASR head on shared streaming representations, jointly predicting ASR tokens and fine-grained turn states at the frame level. We evaluate our method on the bilingual Chinese-English Easy-Turn test sets, and the results demonstrate its effectiveness in achieving accurate turn-taking detection while maintaining low latency.

arXiv

Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs

Yang Yang, Jiawei Chen, Tairan Chen, Zhaoxia Yin

Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inconsistent with the input image, allowing errors to propagate through the reasoning chain and affect the final answer. Existing methods mainly improve spatial reasoning through training or additional spatial information, without considering whether the reasoning process itself is faithful to the model input. Our study shows that unfaithful reasoning chains significantly reduce final-answer accuracy. To address this issue, we propose a modular and training-free framework for spatial reasoning verification and correction. The framework constructs a Spatial Evidence Graph (SEG), which associates atomic spatial evidence extracted from Chain-of-Thought reasoning with visual entities, spatial relations, source steps, and visual evidence. Spatial Evidence Reliability Assessment (SERA) evaluates the reliability of visual evidence based on object existence, localization, and geometric measurements. The framework then identifies the earliest spatial evidence unit contradicted by reliable visual evidence and guides the original MLLM to revise the subsequent reasoning and final answer. Across 15 model-dataset settings, our method achieves an average accuracy of 68.94%, outperforming the compared baselines by 8.55 percentage points on average. Our code will be open-sourced.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.