Search: “agents”

arXiv:2610.12828v1 Announce Type: new Abstract: Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and un

arXiv:2610.11007v1 Announce Type: new Abstract: At the start of every session, LLM agents load a fixed context file, such as exttt{AGENTS.md}. Each loaded token in the file is charged again in every l

arXiv:2609.34565v2 Announce Type: replace Abstract: Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases co

arXiv:2610.12274v1 Announce Type: new Abstract: Text-to-SQL models are commonly trained to map questions directly to static queries, whereas real-world database agents operate through stateful, multi-

arXiv:2610.11030v1 Announce Type: cross Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per ac

arXiv:2610.12403v1 Announce Type: cross Abstract: Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies. Yet most existing approaches remain t

arXiv:2610.10285v1 Announce Type: cross Abstract: In the wake of the increasingly public discussion about AI alignment, recent work has tried to propose specific AI architectures that behave safely. H

arXiv:2610.08862v1 Announce Type: cross Abstract: Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the rema

arXiv:2610.10332v1 Announce Type: new Abstract: Learning from large-model demonstrations offers a way to train small agents that can complete recurring tasks without calling a large model at every ste

arXiv:2610.07614v1 Announce Type: new Abstract: We evaluate whether AI agents can match the reported findings of published biomedical studies using public data. Existing evaluations do not consistentl

arXiv:2606.18537v2 Announce Type: replace Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act reasonably in an environment. However, ob

arXiv:2610.03574v1 Announce Type: new Abstract: We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13

arXiv:2610.02985v1 Announce Type: new Abstract: Embodied agents interacting with the same physical process may maintain heterogeneous, asynchronous, and observer-relative representations. Rather than

arXiv:2610.02491v1 Announce Type: new Abstract: Large language models spend the same amount of computation on every token they generate, regardless of how difficult each token is to produce. Methods s

arXiv:2609.33153v2 Announce Type: replace-cross Abstract: Reported improvements from tools and reusable skills in large language model agents refer to different comparisons. This critical narrative re

arXiv:2610.00372v1 Announce Type: new Abstract: Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Y

arXiv:2609.40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories

arXiv:2609.36608v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-

arXiv:2609.32754v2 Announce Type: replace Abstract: Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequ

arXiv:2609.37025v1 Announce Type: new Abstract: As large language models (LLMs) advance, AI agents are increasingly deployed in open-world environments to tackle complex sequential tasks (e.g., docume

arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful

arXiv:2609.37686v1 Announce Type: new Abstract: Autonomous agents have made rapid progress in general-purpose computer use, but reliable automation of professional industrial engineering remains out o

arXiv:2609.36161v1 Announce Type: cross Abstract: Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open

arXiv:2609.36380v1 Announce Type: new Abstract: A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program w

arXiv:2609.37053v1 Announce Type: new Abstract: Multimodal GUI agents have achieved impressive results on general software benchmarks, yet their ability to operate professional scientific software rem

arXiv:2609.35816v1 Announce Type: cross Abstract: Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional

arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the r

arXiv:2609.36393v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit o

arXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and

arXiv:2609.37125v1 Announce Type: new Abstract: Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition cu

arXiv:2609.36635v1 Announce Type: cross Abstract: Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness a

arXiv:2609.31957v1 Announce Type: new Abstract: Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and

arXiv:2609.35084v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has advanced large language models (LLMs) and is increasingly extending to agentic tasks, where sparse terminal

arXiv:2607.10490v2 Announce Type: replace-cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages

arXiv:2609.33304v1 Announce Type: new Abstract: Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recu

arXiv:2609.31587v1 Announce Type: cross Abstract: We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it

arXiv:2609.31468v1 Announce Type: cross Abstract: LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferen

arXiv:2609.28609v1 Announce Type: new Abstract: Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL me

arXiv:2609.28919v1 Announce Type: new Abstract: Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees: what started as pilots with

arXiv:2609.30186v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both plann

arXiv:2609.27571v1 Announce Type: cross Abstract: Deployment requires an agent to turn application code into a running system whose services connect, become ready, and remain observable. FDE-Bench eva

arXiv:2609.27353v1 Announce Type: new Abstract: Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reprod

arXiv:2607.11433v2 Announce Type: replace Abstract: Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy m

arXiv:2609.26779v1 Announce Type: cross Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context

arXiv:2609.22178v1 Announce Type: cross Abstract: Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task

arXiv:2609.23377v1 Announce Type: cross Abstract: Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be