Restez à la pointe de la tech

Intelligence Artificielle

Whose Ground Truth? Embracing Ambiguity in Human-Centered AI

arXiv:2610.10805v1 Announce Type: new Abstract: As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI. Conventional machine learning and AI systems are largely developed under the assumption that a single definitive ground truth exists, with variability in…

Lire l'article

Intelligence Artificielle

Plan-and-Patch: Diffusion Language Models for Agentic Planning

arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agents must…

Lire l'article

Intelligence Artificielle

Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents

arXiv:2610.10635v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions; on a frozen OpenFly navigator, this \emph{instruction gap} drops success rate (SR) from $31.03\%$ to $11.33\%$. To scale translator training, we prompt a…

Lire l'article

Intelligence Artificielle

The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate

arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is reviewable only if it is confined to the runtime harness (instruction text, tool-call logic and…

Lire l'article

Intelligence Artificielle

Verification and Self-Improvement in Agentic AI: Foundations and Limits

arXiv:2610.10611v1 Announce Type: new Abstract: Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score does not distinguish these mechanisms. We compare these changes through bounded verification with hidden terminal randomness. A stage specifies admissible transcripts, polynomial…

Lire l'article

Intelligence Artificielle

Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice

arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetting: the acting model selects previously observed tool results, replaces each with a short note at its original position, and retains the exact original in a recoverable archive.…

Lire l'article