Search: “reasoning”

arXiv:2606.15974v2 Announce Type: replace Abstract: Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths

arXiv:2608.00515v1 Announce Type: cross Abstract: Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized. We formalize

arXiv:2608.01321v1 Announce Type: new Abstract: Multi-step search is a fundamental capability for search agents, enabling them to iteratively acquire, refine, and integrate external evidence for compl

Just wanted to share my agentic coding benchmark run of DSv4F 0731 at both High and Low reasoning efforts (not Max)... I ran a 109-question subset of Aider Polyglot (the JS/C++/Python languages), base

arXiv:2608.01827v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to

arXiv:2608.01598v1 Announce Type: new Abstract: Simulating human-like Theory of Mind (ToM) has been a longstanding problem in natural language processing (NLP). To address this, existing works introdu

arXiv:2608.02358v1 Announce Type: new Abstract: To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone,

arXiv:2608.01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leadi

arXiv:2607.29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbal

arXiv:2603.06828v2 Announce Type: replace-cross Abstract: We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standa

arXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally

arXiv:2607.27405v1 Announce Type: new Abstract: Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty

arXiv:2601.17151v2 Announce Type: replace-cross Abstract: Frontier models have demonstrated remarkable capabilities in understanding and reasoning with natural-language text, but they still exhibit ma

I've been thinking about building a pipeline to generate reasoning training data for LLMs, but I want to avoid the common failure mode of synthetic data where you just generate the same template with

arXiv:2607.26769v1 Announce Type: new Abstract: Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether

arXiv:2607.25069v1 Announce Type: cross Abstract: Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning. This paper

Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new

arXiv:2607.23806v1 Announce Type: cross Abstract: Improving a language model today means retraining it: enormous compute, a new opaque model each cycle, non-deterministic output. We take the opposite

arXiv:2602.21947v5 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable breadth of knowledge, yet their ability to reason about computational processes remains poorly u

arXiv:2509.03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforceme

arXiv:2607.21725v1 Announce Type: new Abstract: General-purpose robots need to reason about their actions, combining perception, world knowledge, planning, success detection, recovery, and low-level c

arXiv:2607.21617v1 Announce Type: cross Abstract: Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do n

arXiv:2607.22014v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose m

Since a lot more people are trying to build their own multi-GPU machines, I thought I should help to prevent a common mistake people make with building multi-GPU machines. Which is using an Intel cons

arXiv:2607.21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning co

arXiv:2511.05385v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agenti

A Chinese article compiled 52 remarks from Liang Wenfeng’s four-hour investor meeting. I’ve summarised the most important ones below. DeepSeek has one central objective: AGI. This is not the time to m

arXiv:2607.20327v1 Announce Type: new Abstract: Large language models (LLMs) provide strong reasoning capabilities but are expensive to serve at scale, whereas small language models (SLMs) are cheaper

Earlier this month I hosted a fireside chat session at the AI Engineer World's Fair with Cat Wu and Thariq Shihipar from Anthropic's Claude Code team. We talked about Claude Code, Claude Tag, Fable, c

arXiv:2607.13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, c

arXiv:2607.13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-

arXiv:2511.11132v4 Announce Type: replace Abstract: Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA met

arXiv:2607.12217v1 Announce Type: new Abstract: Good tasks are correct, solvable, verifiable, well-specified, and hard for interesting reasons. The best tasks describe a real problem an experienced pr

arXiv:2510.00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with external verifiers or reward models that distinguish

arXiv:2607.12621v1 Announce Type: new Abstract: Recent work has shown that 'Vision-Free'' approaches (representing images as text) can be effective for standard image retrieval tasks. However, it rema

New work led by @FlemmingKondrup and @tomjiralerspong highlights an important vulnerability in chain-of-thought monitoring for agents, I highly recommend giving it a read. Link to the paper: https://a

arXiv:2607.08268v1 Announce Type: new Abstract: High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: compara

arXiv:2607.05680v1 Announce Type: cross Abstract: AI systems are increasingly used to provide legal advice, raising questions about whether laypeople accept guidance from algorithms--especially when t

arXiv:2607.05968v1 Announce Type: cross Abstract: Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either by keyword search over structured profiles, which

arXiv:2607.05690v1 Announce Type: new Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the

arXiv:2607.03550v1 Announce Type: new Abstract: Human reasoning often operates through qualitative concepts expressed by linguistic labels such as high, low, expensive, or cheap, whose interpretation

arXiv:2607.04673v1 Announce Type: new Abstract: Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer lit

arXiv:2607.03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for 'mental' visualizati

arXiv:2607.03847v1 Announce Type: new Abstract: Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems

arXiv:2602.22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to i

arXiv:2606.31484v1 Announce Type: cross Abstract: Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without the need for any re-training. However, existing me