arXiv:2610.08722v1 Announce Type: new Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's...
arXiv:2608. 11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.
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.
The paper introduces ARCBench, a configurable benchmark for measuring rule compliance in language‑model agents that compact long histories to fit context windows. Using ARCBench, the authors find that rule violations after compaction rarely stem from rule deletion; instead, agents often ignore the rule while it remains present in the compacted history. The study shows that the source of violations depends on how the rule is delivered and on the compaction strategy, with targeted compactor attacks significantly increasing violations, and that simply retaining a rule in the compacted summary does not guarantee compliance.
The paper introduces RECAP, a framework for deciding when to retain, compress, or discard parts of a long-horizon agent’s history to improve future performance. RECAP uses matched context interventions, execution-relational prediction, and independent policy certification to evaluate the value of a failure block relative to the current execution. Experiments across five backbones show that RECAP can edit a significant portion of retained checkpoints while maintaining high continuation success and reducing prompt costs.
LLM agents compact long histories to fit their context windows, but the compacted context must still carry the operating rules that govern later actions. Prior work shows that violations rise after co...
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history...
arXiv:2608. 11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks.
arXiv:2608.29028v1 Announce Type: new Abstract: Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. W...
The paper proposes a new reporting standard for attributing agent failures to their history, insisting on intervention‑verified evidence rather than post‑hoc taxonomies. It outlines a method to freeze an executable mid‑trajectory state, alter only the agent’s perceived history, and continue execution to obtain a measured replay certificate. The authors review existing manipulation classes and highlight that while several methods perform interventions, none currently report a quantified replay certificate, and they provide two cautionary examples illustrating the pitfalls of lacking such verification.
arXiv:2608.11242v2 Announce Type: replace-cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We study Side Constraints (SCs), user...
The paper introduces ontological trust, a task‑conditioned property of trajectory prefixes, and presents RGE, an online monitor that decomposes trust into Role, Goal, and Evidence. RGE uses LLMs only for structured task and step representations, while trust updates and interventions are deterministic, producing a replayable and auditable trust trajectory. Evaluated on a cross‑domain corpus, RGE outperforms rule‑, judge‑, and shield‑style baselines, achieving over 93% Drift F1 and maintaining high benign coverage.