arXiv AI
Jul 7
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
arXiv:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
arXiv:2607. 09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness.
Related stories
arXiv AI
Aug 18
AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems
arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.
arXiv Machine Learning
Jun 15
Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems
arXiv:2606. 14155v1 Announce Type: new Abstract: Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights.
arXiv AI
Sep 2
Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers
arXiv:2609. 00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior.
arXiv AI
Jun 9
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models
arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.
arXiv AI
Sep 7
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv AI
Jul 31
Living-Harness Is an Interactive-Agent Evolver
arXiv:2607. 26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions.
arXiv AI
Jul 21
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
arXiv:2607. 16617v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts.
arXiv AI
Sep 11
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
Grounded Continuation introduces a runtime verifier that classifies each utterance in an LLM conversation into one of eight epistemic operations and uses a symbolic engine to maintain a dependency map of claims and their supports. The verifier checks whether a new continuation is grounded by walking this map, a linear-time process that requires no additional LLM calls. On benchmarks such as ReviseQA and MemoryAgentBench, the verifier improves single-hop accuracy for several QA models, even enabling a 7B model to outperform GPT‑4o when guided by the verifier.
arXiv AI
Aug 26
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.
Hugging Face Trending Papers
Jun 29
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive Dashboard
Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn a compression policy that discards evidence or manage context in a layer the agent never sees.
arXiv AI
Aug 25
STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control
arXiv:2608.22538v1 Announce Type: new Abstract: Policy-governed agents must interpret case evidence while following an authorized procedure. We present \textsc{Stage}, an executable-graph framework t...