arXiv AI
State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
ACCORD: Action-Conditioned Contextual Grounding for Language Agents
arXiv:2606. 16432v1 Announce Type: cross Abstract: User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment.
arXiv Machine Learning
Jun 10
From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
arXiv:2606. 09863v1 Announce Type: new Abstract: LLM agents can fail silently by asserting task completion when the environment state shows otherwise.
arXiv AI
Aug 3
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv AI
Sep 17
When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI
The paper evaluates three approaches for emotion recognition in conversation— a low‑cost stacked ensemble, an off‑the‑shelf LLM prompt, and a confidence‑gated hybrid that escalates only uncertain ensemble predictions to the LLM. Across three datasets (IEMOCAP, MELD, CMU‑MOSI), the hybrid consistently outperforms each pure system, achieving higher weighted F1 scores while routing most traffic through the inexpensive ensemble. This results in significant cost savings (≈$10‑85 per million utterances) and provides an interpretable escalation signal tied to emotion or sentiment shifts.
arXiv Computation and Language
3d ago
Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents
arXiv:2609.27353v1 Announce Type: new Abstract: Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely repro...
arXiv Machine Learning
Sep 14
GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents
GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.