The paper "trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories" examines the limitations of outcome-only evaluation for large language model agents. Using a deterministic tool‑using support‑desk environment with a scripted oracle policy and a fault injector, the authors compare five different judging approaches—programmatic rules, outcome‑only, step‑rubric at two model sizes, and a self‑consistency ensemble—on metrics such as detection, step localisation, fault typing, calibration, and cost across 400 trajectories. The study finds that outcome‑only judges miss many silent faults and generate false positives, while step‑rubric judges achieve higher recall with no false alarms but at greater cost, and that none of the judges read the final reply, allowing fabricated promises to evade detection.
"whyItMatters":"The findings highlight that current production‑default outcome‑only evaluations can overlook critical failures in agent behavior, underscoring the need for more nuanced, step‑level judging methods to ensure reliable LLM agent performance."
By Hadi Mohammadi
The paper investigates whether widely used evaluation frameworks for large language models (LLMs) implement a defense called commit‑first judging, which requires a judge to solve a task itself before accepting a candidate answer. Across 24 configurations in eight popular frameworks, none use the full commit‑first method; nine use a weaker variant that is ineffective. In controlled experiments, the weaker variant allowed systems to game the judge, while the full commit‑first approach eliminated this vulnerability but sometimes worsened evaluation when the judge’s own answer was incorrect.
By Idil Gozel
arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.
By Hyundoo Park, Byungho Choi
LLM judges, models that score another system's output, can be gamed by the systems they score. Recent work identifies one defence that works: the judge solves the task itself first and commits to that...
The paper introduces a method for co-evolving inspectable verifiers alongside self-improving agents. By synthesizing verifiers from clustered failures and selecting them based on agreement with a reference set, the authors demonstrate improved held‑out agreement on MBPP+ and outperform a bare LLM judge. They also show that removing anchor guards collapses the verifier into a vacuous grader, yet the collapsed verifier still trains skills effectively, indicating that downstream task scores cannot certify a self‑evolved verifier.
By Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
By Chenyu Zhou
arXiv:2609.25686v1 Announce Type: cross
Abstract: Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent...
By Chenyu Zhang, Wonbin Kweon, Jiawei Han
Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We...
arXiv:2607. 12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists.
By Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
AgentAudit is an open, extensible framework that evaluates the full lifecycle of AI agents, assessing planning, tool selection, execution, memory, and reasoning across ten dimensions such as instruction integrity, security, and alignment. Unlike existing benchmarks that focus on single aspects, AgentAudit analyzes the entire execution trace to attribute failures to specific stages. The framework was tested on five large language models, revealing significant differences in trustworthiness even among models with similar task‑completion performance.
By Shrey Nag, Sachita, Abhishek Kumar Singh, Lipi Goel, Rajeshwar Singh Janwar
Agentic systems have widened the gap between producing candidate outputs and reviewing them. This paper asks a practical architectural question: should domain specialization be built into an evaluator's weights, or into the rule that decides when its judgment can be trusted?
arXiv:2610.19298v1 Announce Type: new
Abstract: Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A progr...
By George Ma, Yuhao Zhang, Bing He, Zeren Shui, Ferhat Erata, Murali Krishna Ramanathan, Somayeh Sojoudi, Hao Zhou