arXiv AI
Jun 17
Dissecting model behavior through agent trajectories
arXiv:2606. 17454v1 Announce Type: new Abstract: AI agent performance is not just a modeling problem, it is fundamentally a systems problem.
Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems
arXiv:2606. 15954v1 Announce Type: cross Abstract: Agentic AI systems act through tools and sub-agents, yet the controls meant to bound their financial and environmental cost still sit on dashboards evaluated beside or after execution.
Related stories
arXiv AI
Jul 2
Self-Evolving Agents with Anytime-Valid Certificates
arXiv:2607. 00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated.
arXiv AI
Jul 14
When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation
arXiv:2607. 10569v1 Announce Type: cross Abstract: Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters.
Hugging Face Trending Papers
Jul 8
The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Falling per-token prices mask the pattern; total spend rises anyway.
arXiv AI
Jul 22
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
arXiv:2607. 19338v1 Announce Type: new Abstract: Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer.
arXiv Machine Learning
Jul 1
Certified Speculative Execution for Untrusted AI Agents
arXiv:2606. 31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers.
arXiv AI
Jul 31
SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation
arXiv:2607. 26313v1 Announce Type: cross Abstract: Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost.
arXiv AI
Jul 9
The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
arXiv:2607. 06906v1 Announce Type: new Abstract: Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value.
arXiv AI
Jun 2
BAGEN: Are LLM Agents Budget-Aware?
arXiv:2606. 00198v1 Announce Type: cross Abstract: While agents are increasingly spending more resources, today agent cost is mostly measured only after execution.
arXiv AI
1d ago
Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
arXiv AI
1d ago
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
arXiv AI
Jun 26
Power Couple? AI Growth and Renewable Energy Investment
arXiv:2603. 26678v2 Announce Type: replace-cross Abstract: AI and renewable energy are increasingly framed as a "power couple," on the premise that surging AI demand will accelerate clean-energy investment, yet concerns persist that AI will entrench fossil-fuel carbon lock-in.