Search: “reasoning”

arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengin

arXiv:2608.29965v1 Announce Type: new Abstract: Large language models can convert medical documents into structured data, but plausible output may still be unsupported by the source. Persisting such o

arXiv:2608.28718v1 Announce Type: cross Abstract: Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) be

arXiv:2608.31100v1 Announce Type: new Abstract: Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent bench

arXiv:2608.30165v1 Announce Type: cross Abstract: Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design

arXiv:2608.30541v1 Announce Type: new Abstract: Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent

arXiv:2608.30456v1 Announce Type: new Abstract: We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the sam

arXiv:2605.05726v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical

arXiv:2608.30005v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific cr

arXiv:2512.16956v3 Announce Type: replace-cross Abstract: Retrieving code functions, classes or files relevant to a user query, bug report or feature request from large codebases is a fundamental chal

arXiv:2608.29886v1 Announce Type: new Abstract: Molecular self-supervised learning uses chemical structures to guide which molecular embeddings should be similar. We study whether explicitly encoding

Super interesting paper from Meta. Long-horizon research agents are coming. But one common problem with research agents today is the lack of originality and how to decide what experiments are worth ex

arXiv:2608.29179v1 Announce Type: cross Abstract: Generative recommendation encodes items as hierarchical semantic identifiers (SIDs) and retrieves the next item through autoregressive decoding. Stand

arXiv:2608.29023v1 Announce Type: new Abstract: Human-robot collaboration describes the process of humans and autonomous agents working together to accomplish common goals. This process is facilitated

arXiv:2606.21803v2 Announce Type: replace Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test ti

That doesn’t mean you can’t get value out of Kimi or Grok or whatever, but it involves you actually knowing some stuff about how to optimize your setup, and a willingness to change direction to switch

arXiv:2608.29706v1 Announce Type: new Abstract: A token's representation is carried through the network layer by layer. The whole vocabulary carried together forms a flow. We fit this flow's equation

arXiv:2608.28664v1 Announce Type: cross Abstract: Despite the success of foundation models in language and vision, their expansion into embodied AI is bottlenecked by a lack of generalized touch sensi

arXiv:2608.30811v1 Announce Type: new Abstract: Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment import

arXiv:2608.28610v1 Announce Type: new Abstract: Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a single-shot decision, neglecting a factor known to pr

arXiv:2510.22588v2 Announce Type: replace-cross Abstract: Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction that

arXiv:2608.28665v1 Announce Type: new Abstract: Recent open-vocabulary segmentation models have advanced semantic perception for UAVs, but predictions from moving aerial platforms can remain temporall

arXiv:2608.28997v1 Announce Type: new Abstract: In May 2026 an OpenAI model produced a counterexample to the Erdos unit distance conjecture. Five mathematicians published a human-verified version the

Very special Training Data drops today: Making Cities Awesome ☺️ We haven’t featured an application company on Training Data in a while. The diffusion of AI is the Most Important Thing, and the highes

arXiv:2608.30530v1 Announce Type: new Abstract: VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility u

arXiv:2608.31035v1 Announce Type: new Abstract: Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptua

arXiv:2603.25269v2 Announce Type: replace Abstract: Hateful content online is often expressed using fact-like, not necessarily correct information, especially in coordinated online harassment campaign

arXiv:2608.29327v1 Announce Type: new Abstract: Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-ef

arXiv:2608.30757v1 Announce Type: new Abstract: Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action

arXiv:2606.16011v2 Announce Type: replace Abstract: Standard accuracy benchmarks evaluate whether large language models (LLMs) reach correct answers. However, they do not test whether models maintain

arXiv:2608.29733v1 Announce Type: new Abstract: Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distin

you can now build @LangChain agents w/ agentic video understanding! google is consistently at the forefront of multimodal processing; this is the video analog of 'agentic vision' token usage + cost is

arXiv:2608.28560v1 Announce Type: new Abstract: Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener g

arXiv:2601.07576v2 Announce Type: replace-cross Abstract: Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance acr

arXiv:2608.27729v1 Announce Type: new Abstract: Function routing -- selecting the correct API call from a fixed catalog given a natural-language request -- is a deployment problem where small students

arXiv:2608.28236v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) enables organizations to forecast future process behavior, such as the next activity and remaining time of ongoing c

arXiv:2608.28058v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) remain prone to hallucinations, producing responses that are irrelevant or inconsistent with the multimodal input.

Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms

Hi all, I have recently been experimenting with different LLM set ups and after everyone was raving about how good Qwen 3.8 27b was, I was inspired to try and get it deploying. After some battling wit

Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, in

arXiv:2608.27902v1 Announce Type: new Abstract: Landing pages are goal-oriented web interfaces that must communicate a target-specific value proposition while organizing information flow, visual hiera

arXiv:2608.28192v1 Announce Type: new Abstract: Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval.

arXiv:2606.14580v2 Announce Type: replace Abstract: Identifying persuasive rhetorical cues is critical across domains, from detecting information manipulation and improving AI safety to advancing publ

arXiv:2608.27512v1 Announce Type: cross Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision

arXiv:2608.27877v1 Announce Type: new Abstract: Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models

arXiv:2608.27678v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) often uses trajectory structure for future-goal sampling and multi-step targets, yet logged traje