Knowledge catalogue
arXiv:2608.24087v1 Announce Type: cross Abstract: Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and
arXiv:2608.24509v1 Announce Type: new Abstract: LLM agents increasingly solve tasks by invoking multiple tools, where parallel execution is essential for low latency but difficult to manage safely. Ex
arXiv:2608.23911v1 Announce Type: new Abstract: Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Po
arXiv:2603.29902v2 Announce Type: replace Abstract: Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way
arXiv:2608.23525v1 Announce Type: new Abstract: Earth-system analysis reconstructs changing physical processes from observations that differ in source, scale, timing, and modality. Natural hazards mak
arXiv:2608.21993v1 Announce Type: new Abstract: We introduce Gated Decoupled Compositional Bandits (GDCB), a family of contextual bandit algorithms with three structural innovations that jointly fall
arXiv:2603.02229v2 Announce Type: replace-cross Abstract: Safety post-training has been studied extensively in single-step 'chat' settings where safety typically refers to refusing harmful requests. W
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relianc
arXiv:2608.22793v1 Announce Type: cross Abstract: Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the
arXiv:2608.20390v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used to answer religious questions, but for Islamic content they carry two serious risks
arXiv:2608.20563v1 Announce Type: cross Abstract: Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services
arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents
arXiv:2607.11818v2 Announce Type: replace-cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful
arXiv:2608.20688v1 Announce Type: new Abstract: The advancement of modern integrated photonics is frequently bottlenecked by device design workflows that rely heavily on manual simulation and expert i
arXiv:2606.15910v2 Announce Type: replace Abstract: A vision-language model can answer a question about a chest radiograph or a pathology slide fluently and confidently while barely using the image, r
arXiv:2608.20314v1 Announce Type: new Abstract: Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted m
arXiv:2608.19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Y
arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning
arXiv:2608.18307v1 Announce Type: new Abstract: Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrum
arXiv:2608.18171v1 Announce Type: new Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We stu
arXiv:2608.18682v1 Announce Type: new Abstract: Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, a
arXiv:2603.25681v2 Announce Type: replace Abstract: As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in
arXiv:2608.19197v1 Announce Type: cross Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environ
arXiv:2608.19072v1 Announce Type: new Abstract: Large language model (LLM) agents can now post-train an LLM end-to-end. They can write code, launch training, evaluate checkpoints, and improve downstre
arXiv:2608.17713v1 Announce Type: new Abstract: Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral prep
arXiv:2608.17393v1 Announce Type: new Abstract: Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execut
arXiv:2608.17146v1 Announce Type: new Abstract: Symbolic planning with PDDL offers a principled framework for long-horizon robot manipulation, but constructing accurate PDDL domain and problem descrip
arXiv:2608.17188v1 Announce Type: cross Abstract: Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context-window quality. This paper presents a practitio
arXiv:2608.17471v1 Announce Type: new Abstract: Recent advances in LLM agents have made them increasingly capable of designing methods for complex AI tasks. This raises two central questions about age
Brex’s summer benchmark shows how quickly the infrastructure behind the agent economy is growing. 14 of the 25 fastest-growing software vendors serve teams building AI products, and Together AI ranks
Does your context compactor actually save anything? If you built or tuned one, this one is worth your time. (bookmark it) Task completion is the standard way to validate compression, and it hides the
arXiv:2608.15032v1 Announce Type: cross Abstract: Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional a
arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long
arXiv:2608.16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a f
We’re sharing the concrete changes we’re making to strengthen monitoring, security, and alignment as capabilities advance. We’ve introduced stronger workload and network isolation, continuous security
arXiv:2608.16370v1 Announce Type: new Abstract: Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by
arXiv:2608.14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after estimates are precise. We introduce optstop, a
arXiv:2608.14068v1 Announce Type: cross Abstract: Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a
arXiv:2608.13926v1 Announce Type: new Abstract: Large language models have made natural language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters
I’m running Ollama on an M4 Pro Mac with 48 GB unified memory and testing local coding models for repository work. Direct Ollama inference is fine. Qwen3.8 27B-MLX runs well enough for me, and the loc
arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.
arXiv:2608.13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process cent
arXiv:2608.12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per t
arXiv:2608.13547v1 Announce Type: new Abstract: LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot disti
arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enfo
arXiv:2608.11552v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one gener
arXiv:2608.11674v1 Announce Type: cross Abstract: On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities,
// Actions Speak Louder Than Words // Multilingual agent evaluation compares final answers and throws the trajectory away. The trajectory fixes cost, latency, failure mode, and auditability. New resea
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed re
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challen
arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that sys
arXiv:2606.16465v2 Announce Type: replace Abstract: AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred.
arXiv:2608.08131v1 Announce Type: cross Abstract: In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activat
DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO, then deploy the fine-tuned model on Together AI for produc
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:2608.07955v1 Announce Type: new Abstract: Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that dem
arXiv:2608.09524v1 Announce Type: cross Abstract: Incident response planning is critical for restoring compromised software systems after cyberattacks. Common practice relies on expert-driven playbook
arXiv:2608.08907v1 Announce Type: cross Abstract: Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then
arXiv:2608.07700v1 Announce Type: new Abstract: Translating a natural-language question into a SPARQL query that can be executed against a large knowledge graph requires resolving lexical ambiguity, g
arXiv:2608.07169v1 Announce Type: new Abstract: Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which strug