Knowledge catalogue
arXiv:2607.22962v1 Announce Type: new Abstract: LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning. A hallucinated
arXiv:2607.22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produc
arXiv:2607.24165v1 Announce Type: cross Abstract: Finding a long document relevant to a multi-part request is not the same as establishing that it contains every requested piece of evidence. We study
arXiv:2607.23442v1 Announce Type: new Abstract: LLM debate is usually evaluated by final answers, but transcripts also reveal whether later turns develop new argumentative content or return to earlier
arXiv:2607.22705v1 Announce Type: new Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations. Existing evaluations usually score segme
arXiv:2607.22569v1 Announce Type: new Abstract: Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, an
arXiv:2506.10292v2 Announce Type: replace-cross Abstract: Training deep learning networks with minimal supervision has gained significant research attention due to its potential to reduce reliance on
arXiv:2607.24459v1 Announce Type: new Abstract: Large language models increasingly solve scientific-computing tasks, but executable feedback from one problem rarely becomes durable capability on subse
arXiv:2607.23292v1 Announce Type: cross Abstract: Deep learning-based visual-infrared fused face detection models are increasingly deployed across a wide range of applications, yet they remain suscept
arXiv:2607.24653v1 Announce Type: new Abstract: We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token
arXiv:2607.24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we intr
arXiv:2607.24365v1 Announce Type: new Abstract: Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible. However, two obstacles limit r
New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr
arXiv:2607.22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode w
arXiv:2607.24190v1 Announce Type: cross Abstract: Social robots that rely on large language models for conversation are unable to retain information across sessions. This absence of memory violates so
arXiv:2607.23023v1 Announce Type: new Abstract: Recent advances in diffusion-based generative models have enabled real-time audio-driven avatar generation and unified audio-visual synthesis, providing
arXiv:2607.23731v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes
arXiv:2607.22588v1 Announce Type: new Abstract: Modern compute-intensive software must migrate across a changing ecosystem of accelerators, programming APIs, compiler stacks, and portability layers, i
arXiv:2607.22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing traject
arXiv:2607.23389v1 Announce Type: cross Abstract: Conventional CAPTCHAs pose puzzles that modern AI systems increasingly solve, while behavioral and cryptographic-attestation defenses carry privacy or
arXiv:2601.16041v2 Announce Type: replace-cross Abstract: In constrained stochastic optimization, one expects that restricting the feasible set, provided it still contains the true parameter, should n
OpenAI field report: eight life-sciences projects used Codex/Claude Code agents; bottleneck shifts from coding to verification.
arXiv:2607.23933v1 Announce Type: cross Abstract: As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces
arXiv:2603.20248v2 Announce Type: replace-cross Abstract: AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust i
arXiv:2505.04260v3 Announce Type: replace-cross Abstract: Personalizing LLM responses typically requires users to articulate their preferences through prompting, which can be burdensome at cold start
arXiv:2607.24519v1 Announce Type: cross Abstract: Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative con
arXiv:2607.24054v1 Announce Type: new Abstract: A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes i
arXiv:2607.23509v1 Announce Type: new Abstract: We present two approaches for predicting tennis match outcomes using topological data analysis and graph theory on ATP singles matches from 2000-2025. T
arXiv:2607.23634v1 Announce Type: cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research ha
arXiv:2607.23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations. They offer a fle
arXiv:2607.21848v1 Announce Type: new Abstract: Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry
arXiv:2607.22165v1 Announce Type: cross Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation a
arXiv:2601.17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evalu
arXiv:2512.06143v2 Announce Type: replace Abstract: Despite a large corpus of recent work on scaling up Gaussian processes, a stubborn trade-off between computational speed, prediction and uncertainty
arXiv:2607.21633v1 Announce Type: new Abstract: Logic Gate Networks (LGNs) implement computation through compositions of Boolean operations, yet unlike classical Boolean circuits, existing LGNs do not
arXiv:2607.18292v2 Announce Type: replace-cross Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability. The knowledge-gap account --
arXiv:2603.05789v5 Announce Type: replace-cross Abstract: Repeated multi-agent interactions require evaluation metrics that capture not only payoff distributions but also their temporal organization.
the paper: babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://
There are a few reasons why problems from International Mathematical Olympiad function as a good benchmark for LLMs: - The problems are new, not included in the training data of any model - Hard math
About 2.5 years ago I tried making an AI comic. It failed. Characters changed, environments drifted, and every page needed manual editing. So I started over with one simple rule: One prompt = one fini
arXiv:2607.21482v1 Announce Type: new Abstract: Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their
arXiv:2607.20441v1 Announce Type: new Abstract: Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their informa
arXiv:2607.21571v1 Announce Type: new Abstract: Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset interna
arXiv:2607.17528v3 Announce Type: replace Abstract: Large language model (LLM) agents are extending electronic design automation (EDA) beyond static RTL generation toward long-horizon, tool-interactiv
arXiv:2607.20692v1 Announce Type: cross Abstract: We present a privacy-preserving framework for synthetic lung CT slice generation developed for the Image-CLEFmed GANs 2026 challenge. The approach com
arXiv:2607.21471v1 Announce Type: new Abstract: Dynamic-scene reconstruction is almost always evaluated inside the observed time window, yet deployment settings such as AR overlays, robot interaction,
Three recent studies show what actually makes an AI agent skill effective: human expertise, compact procedures, tight routing, harness-specific testing, and eval-gated changes—not longer Markdown. The
Built an open-source AI coding agent that was 7%–75% cheaper than a cold 'claude -p' run on 6/6 well-localized tasks across repositories up to ~82k LOC. The biggest difference: Cold agent: 6.83, 207 t
arXiv:2607.20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with au
arXiv:2607.21022v1 Announce Type: new Abstract: Improving video captioning quality typically demands retraining large vision-language models, an expensive and often impractical requirement. Existing t
arXiv:2607.20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formu
arXiv:2607.20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A
arXiv:2607.20767v1 Announce Type: new Abstract: We introduce Rushes, a dataset and benchmark for studying revealed human engagement preferences in interactive narrative environments. Rushes is collect
arXiv:2607.20459v1 Announce Type: cross Abstract: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, mult
arXiv:2501.19337v5 Announce Type: replace Abstract: A name alone measurably reshapes a language model's next-token distribution before a single token is sampled. We measure full-vocabulary Shannon ent
arXiv:2511.12997v2 Announce Type: replace Abstract: Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tas
arXiv:2607.21005v1 Announce Type: new Abstract: Most explanations of training instability focus on learning-rate criticality, typically characterized by the Edge of Stability, beyond which optimizatio
arXiv:2607.19191v1 Announce Type: new Abstract: We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data i
arXiv:2607.19379v1 Announce Type: new Abstract: Prior work has shown that transformers can perform exact Bayesian filtering within a fixed hypothesis class. Can they also perform Bayesian model select
arXiv:2604.01363v2 Announce Type: replace Abstract: We propose that AI automation is a continuum between: (i) crashing waves where AI capabilities surge abruptly over small sets of tasks, and (ii) ris