CRM‑Agent‑Bench is a benchmark that evaluates language agents in customer‑relationship‑management settings by testing 555 stateful, multi‑turn tasks across nine business domains. Each task includes an executable contract with checks on actions, arguments, order, responses, target state, and protected state, and success requires meeting all these checks. The benchmark reports coverage, latency, and cost, showing that evaluated systems achieve 64.32%–83.60% strict success while varying in cost and domain reliability.
arXiv:2607. 25398v1 Announce Type: new Abstract: Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let it govern every action that follows.
The paper introduces PACT, a benchmark designed to evaluate how well enterprise AI assistants follow compliance rules when faced with various pressures such as persistent users or hurried managers. PACT covers twelve regulated domains and forty-eight realistic multi‑turn scenarios, pairing each rule with a shortcut that violates it and applying different pressures across wording and system‑prompt modes. Using PACT, the authors profile six metrics of compliance and aggregate them into a PACTScore, revealing significant variability among 22 LLM models and that even top performers misapply rules 6–10% of the time, with user pressure increasing violations by 65% on average.
arXiv:2608. 19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling.
arXiv:2609.15066v1 Announce Type: cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcem...
arXiv:2607. 01426v1 Announce Type: new Abstract: Autonomous customer-service agents are shifting from conversational interfaces toward operational execution roles: they retrieve firm records, apply service policies, and execute backend writes such as refunds, cancellations, exchanges, order modifications, and reservation changes.
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
Harness-Bench is a diagnostic benchmark that evaluates how different harness configurations affect LLM agent performance in realistic workflows. It tests 106 sandboxed offline tasks across multiple model backends, recording artifacts, execution traces, and usage statistics to analyze completion, process quality, efficiency, and failure behavior. The study finds significant variation in outcomes across model-harness pairings, indicating that agent capability should be reported at the configuration level rather than solely by the base model.
arXiv:2605. 11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims.
In large-scale enterprise settings, centralized multi-agent systems (MAS) are increasingly adopted, in which a coordinator delegates user requests to lightweight, domain-specialized sub-agents. While this architecture improves modularity, scalability, and cost efficiency, its reliability depends not only on accurate routing but also on sub-agents' ability to calibrate their responses to capability constraints.
arXiv:2606. 20529v1 Announce Type: new Abstract: Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies.
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
AgentEval is a system that tracks a contract-bound assessment record throughout a stateful agent’s tool execution, capturing state, events, and evidence to determine whether obligations are satisfied, violated, or unresolved. In 32 tool‑world administrations, independent checks confirmed all 30 complete episodes, while controlled interventions on 48 evidence views uncovered 36 binding faults that hash‑only checks missed. A public‑benchmark study on 192 held‑out executions identified ten completed subgoals within broader task failures and highlighted the impact of missing evidence on overall task success.