arXiv AI
Jul 7
Auto: The AGI Compiler
arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.
TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.
Related stories
arXiv AI
Jun 10
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
arXiv:2606. 10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved through iterative error analysis.
arXiv AI
Jun 10
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.
arXiv AI
Aug 7
Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay
arXiv:2608. 05784v1 Announce Type: new Abstract: Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the user said, not what the user did.
arXiv AI
Aug 12
Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
arXiv AI
Jun 6
From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability
arXiv:2606. 05252v1 Announce Type: cross Abstract: Security teams routinely simulate attacks against their own systems to check whether their monitoring would catch a real intruder.
arXiv Machine Learning
Jun 25
Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
arXiv AI
Aug 7
Runtime Observability for Heterogeneous Attention Memory
arXiv:2608. 05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression.
arXiv AI
Jul 21
AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows
arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.
arXiv Machine Learning
Jun 17
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
arXiv:2606. 17182v1 Announce Type: new Abstract: Multi-agent LLM systems share state through memory stores, vector indices, and tool registries.
arXiv AI
Jul 7
Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
arXiv:2604. 00392v2 Announce Type: replace-cross Abstract: Agents that synthesize their own tools ship a second artifact alongside each answer: a software library that future tasks reuse, compose, and depend on.
arXiv AI
Jun 10
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces
arXiv:2606. 10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes.