Search: “agents”

arXiv:2609.23735v2 Announce Type: new Abstract: Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim ass

arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model

arXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned,

arXiv:2609.23806v1 Announce Type: new Abstract: Many knowledge-work benchmarks are constructed around individual tasks, with the context needed for each task selected together with or after the task h

arXiv:2609.23808v1 Announce Type: new Abstract: While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create

arXiv:2609.24144v1 Announce Type: new Abstract: Group-relative reinforcement learning compares rollouts of the same prompt, but independent environment noise can obscure these comparisons. We study pa

arXiv:2609.24071v1 Announce Type: new Abstract: Chart reasoning agents are increasingly used to extract actionable insights in critical domains, achieving state-of-the-art performance on multiple benc

arXiv:2609.24890v1 Announce Type: new Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with func

arXiv:2609.23570v1 Announce Type: cross Abstract: Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluation

arXiv:2609.22259v1 Announce Type: new Abstract: Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/with

arXiv:2609.21944v1 Announce Type: cross Abstract: In recent years, quantum game theory has gained significant attention as a framework for studying decision-making in multi-agent systems using quantum

arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Rea

arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitw

arXiv:2609.20152v1 Announce Type: new Abstract: Generally, most voice agents are cascaded systems, i.e., an ASR model transcribes the caller's audio, a language model reads the transcript and decides

arXiv:2609.20754v1 Announce Type: new Abstract: Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing ret

arXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been t

arXiv:2609.17552v1 Announce Type: new Abstract: Moral-reward RL can make language-model agents more cooperative, but whether that alignment survives adversarial persona pressure is unknown. Such attac

arXiv:2609.13667v1 Announce Type: new Abstract: Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings,

arXiv:2609.13637v1 Announce Type: new Abstract: Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider

arXiv:2609.13287v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive fo

arXiv:2609.08566v1 Announce Type: new Abstract: KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however,

arXiv:2609.05901v1 Announce Type: cross Abstract: Autonomous LLM agents can turn untrusted content into effectful actions such as payments and permission changes. If the same process interprets this c

arXiv:2609.09778v1 Announce Type: new Abstract: Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic bounda

arXiv:2609.07029v1 Announce Type: new Abstract: Localizing a font into new languages is a highly intricate task requiring precise design adaptation of glyphs, color/texture, and spacing/kerning, from

arXiv:2609.06966v1 Announce Type: new Abstract: Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison traini

arXiv:2609.09113v1 Announce Type: cross Abstract: While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a mis

arXiv:2609.05911v1 Announce Type: cross Abstract: Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize

arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing de

arXiv:2607.09773v2 Announce Type: replace Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although

arXiv:2609.04802v1 Announce Type: cross Abstract: Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in na

arXiv:2609.05232v1 Announce Type: new Abstract: Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine w

arXiv:2609.03423v1 Announce Type: new Abstract: Full-duplex voice agents must continuously decide when to listen, backchannel, interrupt, handle speech overlaps, take the floor, and yield. Existing be

arXiv:2609.04128v1 Announce Type: new Abstract: Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesiz

arXiv:2609.02889v1 Announce Type: new Abstract: A growing body of work improves frozen large language models (LLMs) as agents by evolving their harness: the textual scaffolding around the model, inclu

arXiv:2609.02042v1 Announce Type: new Abstract: Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round

arXiv:2609.02265v1 Announce Type: new Abstract: Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information c

arXiv:2609.01038v1 Announce Type: new Abstract: A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measur

arXiv:2608.28632v1 Announce Type: new Abstract: Large language model agents can discover alphas, yet current methods have three weaknesses. The search cannot adapt during the run, automation usually e

arXiv:2510.03204v2 Announce Type: replace Abstract: Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens

arXiv:2608.30916v1 Announce Type: new Abstract: Agent evaluations often use one benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selec

arXiv:2509.23155v3 Announce Type: replace Abstract: Robotic manipulation benefits from foundation models that describe goals, but today's agents still lack a principled way to learn from their own mis

arXiv:2608.22833v1 Announce Type: cross Abstract: Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations

arXiv:2608.22974v1 Announce Type: new Abstract: Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks,

arXiv:2608.22960v1 Announce Type: new Abstract: Coding agents are increasingly evaluated not only by whether they solve a task, but also by how they execute it. However, existing process-level evaluat

arXiv:2608.20729v1 Announce Type: new Abstract: Language-model agents can improve after failure or carry text across episodes without revising what counts as success. We study the narrower attribution

arXiv:2608.19803v1 Announce Type: cross Abstract: Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing metho