Knowledge catalogue
8/19, join us for the #ACMTechTalk, 'From Conventional LLMs to Reasoning Models to Agents,' w/AI & LLM Research Engineer @rasbt. ACM Practitioner Board Co-Chaior @marlene_zw (@Microsoft) will moderate
arXiv:2608.11506v1 Announce Type: cross Abstract: Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Bar
arXiv:2608.12273v1 Announce Type: cross Abstract: LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progre
arXiv:2608.10198v1 Announce Type: new Abstract: Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reaso
We have her dash camera which shows they are lying. The agents are wearing body cameras and should have dash cameras of their own. If what they say happened was true they wouldn’t be issuing statement
arXiv:2608.09025v1 Announce Type: new Abstract: Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy. We present SAGE-Fin, a f
arXiv:2608.08852v1 Announce Type: new Abstract: AI agents can now solve problems, answer like subject experts, and generate long-form multimodal content. However, whether they can adapt a lesson to fi
arXiv:2608.05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajector
I’ve been thinking about how agents can learn inside world models for years. We decided to scale up our RSI Lab to bridge recursive self-improvement with physical AI and robotics. We are looking for f
arXiv:2608.08184v1 Announce Type: new Abstract: Large multimodal agents (LMAs) are increasingly proposed for intelligent transportation systems (ITS), but existing studies often conflate multimodality
arXiv:2608.00326v2 Announce Type: replace Abstract: Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields includ
arXiv:2608.09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artif
arXiv:2608.07959v1 Announce Type: new Abstract: Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multi
arXiv:2608.08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said. Flat
arXiv:2608.08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model dist
arXiv:2608.06948v1 Announce Type: new Abstract: AI models are becoming increasingly adept at understanding and processing spatial information, thereby facilitating agentic problem-solving in spatial t
arXiv:2608.05891v1 Announce Type: new Abstract: Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horiz
arXiv:2608.05490v1 Announce Type: new Abstract: Autonomous agents now carry out entire data analyses, selecting cohorts, joining tables, and fitting models with little step-by-step supervision. When s
arXiv:2608.05219v1 Announce Type: new Abstract: Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response
arXiv:2608.05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: p
arXiv:2608.04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it. After an upstr
arXiv:2608.05095v1 Announce Type: new Abstract: Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue t
arXiv:2608.02694v1 Announce Type: new Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions. Yet editing quality is subjective, admits mul
arXiv:2608.03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attribu
arXiv:2608.03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typic
arXiv:2608.02642v1 Announce Type: cross Abstract: Accelerating scientific discovery is among the most consequential applications of AI, and computational biomolecular simulation stands out as a partic
arXiv:2608.03474v1 Announce Type: new Abstract: Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks pre
Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously unknown incidents tha
arXiv:2608.02356v2 Announce Type: replace Abstract: Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not
arXiv:2608.03699v1 Announce Type: new Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existin
arXiv:2608.03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon i
arXiv:2607.29440v1 Announce Type: new Abstract: Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions.
Lily Hay Newman / Wired: Experts say US law is unprepared for rogue AI agents and models, as recent OpenAI and Anthropic incidents raise questions over legal liability and repercussions — Both major A
arXiv:2607.27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it n
New research from Microsoft. This one is on training computer-use agents at scale. Recent pipelines generate synthetic environments in bulk, which moved the bottleneck from how many exist to what is i
arXiv:2607.26910v1 Announce Type: new Abstract: Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high
arXiv:2607.26865v1 Announce Type: cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, a
A benchmark score reflects the model as well as the harness and settings used to run it. For long-running agents, retaining reasoning and compacting context lets the model build on what it has already
BREAKING: Grok 4.5 (high) ranks #1 on the HighWalk benchmark, which tests how well AI agents update technical specifications from code changes. Grok delivered the best combination of quality and opera
arXiv:2607.25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection
arXiv:2607.24779v1 Announce Type: new Abstract: Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL
arXiv:2607.25132v1 Announce Type: new Abstract: A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help ex
arXiv:2607.11346v3 Announce Type: replace Abstract: Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP const
arXiv:2607.20528v1 Announce Type: new Abstract: Online recommendation platforms increasingly use Large Language Models (LLMs) to extract structured features from ad creatives. While deploying a single
arXiv:2607.20926v1 Announce Type: new Abstract: Scientific research involves complex information-seeking and reasoning workflows across heterogeneous sources. However, existing benchmarks primarily em
arXiv:2602.10226v2 Announce Type: replace-cross Abstract: Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyper
arXiv:2607.19359v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving
Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching LangSmith tracing for 4 voice frameworks: 🎙️ @pipecat_ai 🎙️ @livekit 🎙️ @OpenAI Realtime 🎙️ @GeminiApp L
congrats on the launch! As the task horizons on agents gets longer, we need more work evaluating and training models to be better in long-running, open-ended, evolving real-world environments. Today w
arXiv:2607.07985v1 Announce Type: cross Abstract: We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform,
The Hermes Desktop app can now discover and connect to your Hermes Cloud agents. Sign in with Nous Portal and any active Cloud instances are auto-discovered. http://portal.nousresearch.com/cloud Media
As a result, we can show that open-source-derived models are not inherently untrustworthy. They can be suitable for production agents with careful development, realistic evals, and targeted mitigation
Got this setup in Claude Code to trace models routed through @merge_api! Being able to trace what your agents are doing is so valuable, I love open source 🙌 We built a plugin that traces every Claude
langsmith for coding agents We built a plugin that traces every Claude Code session straight into LangSmith. Three commands, one JSON block, and every message, tool call, and subagent run shows up as
Massive day for us @OpenAI: - GPT-5.6 SOTA at ~everything & by far most token efficient - Agents for everyone in the new ChatGPT app Work and Codex modes - Work mode available on desktop (most powerfu
Lily Mae Lazarus / Fortune: Mercor acquires Deeptune, which builds reinforcement learning environments for AI agents, three months after CEO Brendan Foody backed Deeptune's $43M Series A — Brendan Foo
arXiv:2607.07436v1 Announce Type: new Abstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the stru
Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency. https://x.ai/news/gr
This Databricks blog post evaluates the performance and capabilities of coding agents when applied to real-world scenarios involving their own multi-million line codebase, likely assessing metrics suc
Busy couple days ahead! Today, @nvidia Nemotron 3 Ultra support for @LangChain Deep Agents at a fraction of the cost -w/ Quick Start Prompt Tomorrow is Wikimania🔥 @hwchase17 is chatting with with @Bra