Search: “reasoning”

arXiv:2606.07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We identify a data-induced failure mode, PhysHack, in wh

arXiv:2606.09091v1 Announce Type: cross Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm. By using a stronger teacher model to provide dense, fine-gra

arXiv:2606.07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse 'turtle' bias toward defensive p

arXiv:2606.08633v1 Announce Type: new Abstract: Long-horizon maritime trajectory prediction is important for shipping management, logistics planning, and maritime risk analysis, yet month-level foreca

arXiv:2606.07299v1 Announce Type: new Abstract: Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame prob

arXiv:2606.06532v1 Announce Type: new Abstract: Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient me

arXiv:2603.24481v2 Announce Type: replace Abstract: Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful

arXiv:2606.07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect usi

arXiv:2606.06538v1 Announce Type: new Abstract: In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types

arXiv:2601.21162v2 Announce Type: replace-cross Abstract: Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing

arXiv:2606.05979v1 Announce Type: new Abstract: We propose world-language-action (WLA) models as a new class of embodied foundation models. WLA takes textual instructions, images, and robot states as

arXiv:2606.04061v1 Announce Type: new Abstract: Large-scale web-harvested datasets have fueled the progress of cross-modal retrieval but inevitably suffer from noisy correspondence, which severely deg

arXiv:2606.05025v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differ

arXiv:2606.04442v1 Announce Type: cross Abstract: AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehe

arXiv:2603.00667v3 Announce Type: replace Abstract: Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using vision-language

arXiv:2606.03066v1 Announce Type: new Abstract: The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social sta

arXiv:2606.03435v1 Announce Type: new Abstract: Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readout

arXiv:2606.02386v1 Announce Type: new Abstract: Protein language models (PLMs) are passive oracles: they generate sequences in a single forward pass with no mechanism to consult external biophysical f

arXiv:2606.00020v1 Announce Type: cross Abstract: Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack special

arXiv:2606.00445v1 Announce Type: cross Abstract: Dark vessel detection requires fusing what vessels report through AIS with what satellites observe through radar and optical sensors. DarkVesselNet is

arXiv:2606.01565v1 Announce Type: cross Abstract: Vision-Language Navigation in Continuous Environments (VLN-CE) poses a formidable challenge for autonomous agents, requiring seamless integration of n

arXiv:2606.02020v1 Announce Type: new Abstract: This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of explorati

arXiv:2605.30641v1 Announce Type: cross Abstract: Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought),

arXiv:2605.30538v1 Announce Type: new Abstract: Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records

arXiv:2605.30415v1 Announce Type: cross Abstract: We investigate how domain adaptation reshapes explanatory behavior in language models using historical cosmology as a controlled setting. In Phase 1,

arXiv:2605.31446v1 Announce Type: cross Abstract: Aspect Sentiment Triplet Extraction (ASTE) aims to identify aspect terms, opinion terms, and sentiment polarities as structured triplets, providing es

arXiv:2603.00068v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined eve

arXiv:2605.31404v1 Announce Type: cross Abstract: Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster map

arXiv:2605.29170v1 Announce Type: cross Abstract: Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We intr

arXiv:2605.29126v1 Announce Type: cross Abstract: A linear probe can decode a representation almost perfectly and yet be completely irrelevant to how the model uses it. On calendar-date duration reaso

arXiv:2605.27860v1 Announce Type: new Abstract: Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidenc

arXiv:2605.27764v1 Announce Type: cross Abstract: Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instruc

arXiv:2603.05642v2 Announce Type: replace-cross Abstract: Open-world interactive object search in household environments requires understanding semantic relationships between objects and their surroun

arXiv:2605.27765v1 Announce Type: cross Abstract: Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by lev

arXiv:2605.28459v1 Announce Type: new Abstract: Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically

arXiv:2605.28433v1 Announce Type: new Abstract: Role-based LLM multi-agent systems need adaptive role pools, yet adapting such systems is not merely a matter of prompt optimization: roles often carry

arXiv:2605.27110v1 Announce Type: cross Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal discl

arXiv:2605.27000v1 Announce Type: cross Abstract: Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@K as the canonical metric. Yet the

arXiv:2602.08586v3 Announce Type: replace Abstract: Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or

arXiv:2509.21552v2 Announce Type: replace-cross Abstract: Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate

arXiv:2605.27246v1 Announce Type: cross Abstract: This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line

arXiv:2602.17003v2 Announce Type: replace-cross Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail

arXiv:2605.24331v1 Announce Type: new Abstract: Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the

arXiv:2605.25958v1 Announce Type: new Abstract: This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anoma

arXiv:2605.23238v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior i

arXiv:2605.21600v1 Announce Type: new Abstract: Computational antibody CDR design methods condition on antigen structure to generate binding loops, yet existing architectures conflate two fundamentall