Search: “reasoning”

This sub is, needless to say very niche and skewed towards the high end. There are tons of extremely high end setups here with multiple gpu's etc. Even 24GB is out of reach of most people financially,

arXiv:2408.07702v2 Announce Type: cross Abstract: Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's q

arXiv:2507.21931v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. R

arXiv:2609.15989v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model 'actor' is inspected by a 'monitor' (often another

arXiv:2603.29396v2 Announce Type: replace Abstract: Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appr

arXiv:2609.09187v1 Announce Type: cross Abstract: Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online

arXiv:2602.00288v4 Announce Type: replace Abstract: Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) mas

arXiv:2609.02049v1 Announce Type: cross Abstract: LLMs latent-state reasoning methods replace discrete intermediate tokens with continuous states, such as weighted mixtures of token embeddings, to ret

arXiv:2609.01059v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. Howe

arXiv:2608.29588v1 Announce Type: new Abstract: Reasoning over text-attributed graphs (TAGs) requires large language models (LLMs) to combine a node's text with evidence distributed across its neighbo

arXiv:2608.29431v1 Announce Type: new Abstract: Localized Representation Steering (LRS) is widely used to correct reasoning pathologies in large language models. However, standard benchmark evaluation

arXiv:2608.30653v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. Howeve

arXiv:2608.30396v1 Announce Type: new Abstract: Long-horizon physical-world agents must reason over distant goals while grounding decisions in reliable closed-loop behavior. Today's foundation models

arXiv:2608.30258v1 Announce Type: cross Abstract: Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combining large language models (LLMs) and symbolic solve

arXiv:2608.30395v1 Announce Type: new Abstract: As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inf

arXiv:2608.26141v1 Announce Type: new Abstract: Multimodal large language models have demonstrated strong document reasoning capabilities by incorporating explicit thinking processes. While this capab

arXiv:2608.27420v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves LLM reasoning but often causes a drop in policy entropy, leading to narrowe

arXiv:2608.25398v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong abilities in solving diverse visual and textual reasoning tasks. However, their develo

arXiv:2512.13979v2 Announce Type: replace Abstract: Large reasoning models achieve strong performance on diverse tasks by producing extended chains of thought. Self-reflection, the ability to review a

arXiv:2608.20083v1 Announce Type: cross Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle

arXiv:2608.13567v1 Announce Type: new Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about o

arXiv:2608.14420v1 Announce Type: new Abstract: Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at infe

arXiv:2608.13129v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including

arXiv:2608.10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests l

arXiv:2608.09271v1 Announce Type: cross Abstract: Group-based reinforcement learning objectives such as GRPO can allocate learning signal poorly across prompt difficulty: under binary rewards, group n

I have various quants of this model and am curious how they perform. can anyone recommend which benchmark would be a good test case for quantization effects? Maybe that can be completed with about 1 m

arXiv:2608.01314v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthe

arXiv:2512.03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally opt

cli : persist reasoning_content in chat history (#26362) cli : persist reasoning_content in chat history llama-cli collected reasoning from the stream for display but only stored assistant content in

arXiv:2607.28225v1 Announce Type: new Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, h

arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG sys

arXiv:2607.26518v1 Announce Type: new Abstract: Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic unc

arXiv:2607.25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predic

Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. It put the systems in a sandboxed environment without an internet

arXiv:2607.22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reaso

arXiv:2607.24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this

arXiv:2607.19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that. In clu

arXiv:2607.13548v1 Announce Type: new Abstract: Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces

arXiv:2607.10383v2 Announce Type: replace-cross Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse emb

arXiv:2409.05559v2 Announce Type: replace Abstract: Large language models (LLMs) have developed rapidly, and their reasoning capabilities have become a hot research topic. However, there is still limi

arXiv:2607.01951v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat

arXiv:2510.09517v2 Announce Type: replace Abstract: Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do no

arXiv:2606.28574v1 Announce Type: cross Abstract: When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability

arXiv:2602.13562v2 Announce Type: replace-cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measu

AI browsers can be manipulated through prompt injection or memory poisoning to create false operational contexts where they bypass security guardrails, treating harmful actions as game logic rather th

Swyx posted about being invited to deliver a keynote address at a conference, expressing humorous surprise at being selected for this speaking role. The post likely reflects on the unexpected opportun