The paper introduces a multi‑resolution framework for interpreting human behavioral traces in workplace agents, arguing that a single summary is insufficient. It defines a hierarchy of semantic operators, motifs, episodes, and day‑level rhythms, and applies this to 667 million events from a commercial productivity suite, yielding 120 operator types, thousands of motifs, 25 episode types, and five rhythm archetypes. Validation shows the taxonomy is structurally stable and improves next‑episode prediction by 17% macro‑F1 over a flat baseline, while ablation experiments demonstrate that different questions require different temporal resolutions.
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts.
The paper introduces a live trace model that incrementally folds an append‑only event ledger into typed run state, producing per‑consumer views for both human observers and the agent itself. Evaluations show that for observers, the compiled view reduces input tokens by 14–15× and cost by 5–7× while improving accuracy from 0.48 to 0.85–0.87. For agents, maintaining running statistics in per‑step state enables success on 120‑link sequential tasks where full‑context prompting fails, and a prompt‑level scratchpad matches the fold’s accuracy at lower cost.
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:2606. 15405v1 Announce Type: cross Abstract: Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user.
arXiv:2608. 11775v1 Announce Type: new Abstract: Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood.
arXiv:2607. 21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs.
arXiv:2608. 20319v1 Announce Type: cross Abstract: Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable models of how everyday work is done.
VeriPhy is an auditable physical‑verification system that evaluates generated video by compiling prompts into typed physical obligations and a statically validated execution plan before any frames are observed. During execution, it gates calls to frozen low‑level experts (e.g., segmentation, tracking, counting, depth, OCR, audio‑event detection) and returns provenance‑carrying evidence records, which are mapped to a three‑valued state (supported, contradicted, unknown) with full traceability. On a 1,500‑clip corpus of human‑annotated flaw records, VeriPhy accounts for 228 failures out of 304, outperforming a published question‑decomposition evaluator that accounts for 164, while also providing auditable evidence for each verdict.
arXiv:2606. 09483v1 Announce Type: cross Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time.
arXiv:2607. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.
ReFract is a new benchmark that tests whether language model agents can act appropriately based on a user’s role, a capability called Perspective Awareness. It contains 150 expert‑validated entries derived from anonymized domain support queries, and uses Text World Models to simulate the agents’ operating environments and generate perspective‑aware action trajectories. Current state‑of‑the‑art LLMs solve at most 69% of the tasks, with over half of their trajectories attempting perspective‑violating actions.