Knowledge catalogue
arXiv:2606.04223v1 Announce Type: new Abstract: Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue th
arXiv:2606.04474v1 Announce Type: new Abstract: Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this modality gap is not a uniform cognit
arXiv:2606.04751v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in scientific tasks. Yet whether these systems can effectively engage in for
arXiv:2606.04823v1 Announce Type: new Abstract: Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizon
95% token reduction. 30x faster execution. 90%+ task completion. Today at #MSBuild, we announced a major shift to move reasoning upstream: Pinecone Nexus now integrates directly with @Microsoft OneLak
arXiv:2606.03624v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions,
arXiv:2606.03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many s
arXiv:2606.02994v1 Announce Type: new Abstract: ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We intro
arXiv:2606.02907v1 Announce Type: cross Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning
arXiv:2606.03099v1 Announce Type: cross Abstract: Deep Image Search requires multi-step reasoning over rich contextual cues, such as time, location, and event relations. However, most existing LLM-bas
arXiv:2606.03969v1 Announce Type: cross Abstract: Reliable uncertainty communication is critical to the trustworthiness of LLMs, yet faithful calibration (FC)--the alignment between models' intrinsic
arXiv:2606.00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under tea
arXiv:2606.01464v1 Announce Type: new Abstract: Despite expanding their multilingual coverage, the advanced reasoning capabilities of LLMs remain largely confined to a few high-resource languages like
arXiv:2604.17621v2 Announce Type: replace Abstract: Many real-world questions appear deceptively simple yet implicitly demand two capabilities: (i) systematic coverage of a bounded knowledge universe
arXiv:2603.26779v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet they struggle with spatial tasks that require mental sim
arXiv:2606.00206v1 Announce Type: new Abstract: Post-training quantization (PTQ) is widely used to deploy large language models efficiently, but its effect on reasoning models is not well understood.
arXiv:2606.02506v1 Announce Type: new Abstract: The VRR-QA challenge evaluates visual relational reasoning in videos, where answers often depend on implicit spatial relations, event boundaries, target
arXiv:2512.07795v2 Announce Type: replace Abstract: Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same model, strategy, and task can produce meaningfully different
arXiv:2606.01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language mo
arXiv:2606.01912v1 Announce Type: new Abstract: Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferen
arXiv:2606.00376v1 Announce Type: new Abstract: Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks, not due to preference biases, but limits rooted in th
arXiv:2606.01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer. That
arXiv:2606.00133v1 Announce Type: new Abstract: World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artifici
arXiv:2603.07751v2 Announce Type: replace-cross Abstract: Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks
arXiv:2605.30900v1 Announce Type: new Abstract: Current multimodal models handle static image recognition well, but intuitive physical reasoning remains a weakness. Predicting how objects will move an
arXiv:2605.31031v1 Announce Type: new Abstract: Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce Gr
arXiv:2602.07905v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While
arXiv:2511.16940v3 Announce Type: replace Abstract: Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individua
arXiv:2508.20478v2 Announce Type: replace Abstract: Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often re
arXiv:2605.29568v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during seq
arXiv:2605.28888v1 Announce Type: cross Abstract: Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide
arXiv:2605.30214v1 Announce Type: new Abstract: Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about referenc
arXiv:2605.29512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended intera
arXiv:2605.29327v1 Announce Type: new Abstract: Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high trai
arXiv:2605.29068v1 Announce Type: new Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrai
arXiv:2602.11065v2 Announce Type: replace-cross Abstract: Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing thi
arXiv:2605.29087v1 Announce Type: new Abstract: Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained
arXiv:2605.30011v1 Announce Type: cross Abstract: Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain
arXiv:2605.29190v1 Announce Type: cross Abstract: Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why i
arXiv:2605.28028v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is widely used for training reasoning models, but updating all sampled completions in each group incurs substa
arXiv:2605.28292v1 Announce Type: new Abstract: Implicit Chain-of-Thought (CoT) reduces the inference cost of large language models by internalizing the explicit rationales. However, existing approach
arXiv:2605.28487v1 Announce Type: new Abstract: Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten sy
arXiv:2605.27965v1 Announce Type: new Abstract: Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction
arXiv:2603.09551v2 Announce Type: replace Abstract: While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reason
arXiv:2605.26621v1 Announce Type: cross Abstract: Volumetric Reasoning Segmentation (VRS) aims to segment a target region in a 3D medical scan from a free-form clinical query, where the referent is of
arXiv:2605.26177v1 Announce Type: cross Abstract: Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on e
arXiv:2605.26733v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: perfor
arXiv:2605.26530v1 Announce Type: new Abstract: Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations
arXiv:2605.24573v1 Announce Type: new Abstract: Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth o
arXiv:2602.01992v4 Announce Type: replace Abstract: Analogy is a central faculty of human intelligence, enabling abstract patterns discovered in one domain to be applied to another. Despite its centra
arXiv:2602.00491v2 Announce Type: replace Abstract: Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it r
arXiv:2605.24844v1 Announce Type: new Abstract: While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evoluti
arXiv:2605.24549v1 Announce Type: new Abstract: Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adapta
arXiv:2605.25480v1 Announce Type: new Abstract: LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when ev
arXiv:2605.24468v1 Announce Type: new Abstract: Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and
arXiv:2605.25954v1 Announce Type: cross Abstract: Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging
arXiv:2602.01914v2 Announce Type: replace Abstract: Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as mode
arXiv:2605.23216v1 Announce Type: new Abstract: Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception t
arXiv:2605.23170v1 Announce Type: cross Abstract: Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not cont
arXiv:2605.21851v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a sin