3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.14939v1 Announce Type: new Abstract: GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individual reasoning tokens.
arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a standardized interf…
arXiv:2610.14959v1 Announce Type: new Abstract: Formulaic alpha mining seeks to discover executable expressions that capture predictive market signals in a vast, noisy search space.
arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state.
arXiv:2610.14980v1 Announce Type: new Abstract: We present a generator of Thai klon pad verse, one stanza from a short topic, and evaluate it against human verse on held-out topics.
arXiv:2610.15008v1 Announce Type: new Abstract: Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization.
arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before.
arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks.
arXiv:2610.15129v1 Announce Type: new Abstract: Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestur…
arXiv:2610.15150v1 Announce Type: new Abstract: Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback.
arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill.
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row.
arXiv:2610.15221v1 Announce Type: new Abstract: AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation…
arXiv:2610.15235v1 Announce Type: new Abstract: Despite remarkable progress in language understanding and generation, decoder language models continue to exhibit striking failures on numerical data.
arXiv:2610.15239v1 Announce Type: new Abstract: Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions.
arXiv:2610.15259v1 Announce Type: new Abstract: Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought.
arXiv:2610.15292v1 Announce Type: new Abstract: LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge.
arXiv:2610.15322v1 Announce Type: new Abstract: Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable artificial intelligence…
arXiv:2610.15403v1 Announce Type: new Abstract: Crowdsourced disaster imagery provides timely, ground-level observations when conventional disaster mapping is delayed or incomplete, yet its geographic value depends on wh…
arXiv:2610.15407v1 Announce Type: new Abstract: An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes.
arXiv:2610.15481v1 Announce Type: new Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agent.
arXiv:2610.15501v1 Announce Type: new Abstract: Large language models make decisions through parallel prefill and sequential decoding.
arXiv:2610.15529v1 Announce Type: new Abstract: Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use.
arXiv:2610.15575v1 Announce Type: new Abstract: Diffusion models have been widely used for various generative tasks.
arXiv:2610.15582v1 Announce Type: new Abstract: We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents.
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synth…
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively sufficient for the curre…
arXiv:2610.15685v1 Announce Type: new Abstract: Conventional distillation transfers capability through teacher-generated demonstrations.
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights.
arXiv:2610.15710v1 Announce Type: new Abstract: Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim.
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centr…
arXiv:2610.15882v1 Announce Type: new Abstract: A stored fact may stop being valid when a user changes a preference or an event replaces an earlier one.
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass.
arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways.
arXiv:2610.15994v1 Announce Type: new Abstract: Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are sparse.
arXiv:2610.16015v1 Announce Type: new Abstract: The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems.
arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence.
arXiv:2610.16117v1 Announce Type: new Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise.
arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy.
arXiv:2610.16140v1 Announce Type: new Abstract: Transportation planning has traditionally required substantial expertise in network modeling, traffic assignment, and optimization.
arXiv:2610.16141v1 Announce Type: new Abstract: LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its associatio…
arXiv:2610.16145v1 Announce Type: new Abstract: Agent frameworks can persist checkpoints, trace tool calls, and limit resource use, but these facilities often assign different identities to execution, governance, and rep…
arXiv:2610.16155v1 Announce Type: new Abstract: Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking failures that arise…
arXiv:2610.16280v1 Announce Type: new Abstract: Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs.
arXiv:2610.16288v1 Announce Type: new Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents.
arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position signals bound to the…
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate comp…
arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit?
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the conte…
arXiv:2610.16343v1 Announce Type: new Abstract: Multi-agent debate has shown promise for improving the reasoning of large language models, yet recent theory suggests its benefits are highly regime-dependent.