AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data is a rich, underused signal for closing the gap to individual expertise. In this work, we propose test-time adaptation through human-agent interaction (TAHI), which integrates these signals into agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module. We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks. Our agents improve solo task success by 4.5-20.9% within only tens of tasks. Meanwhile, our evolving rubric module serves as a scalable annotation tool, creating evaluation rubrics that catch 16.0-22.3% more failures than those from LMs or humans alone. While agents are adapted towards individuals, we show these personalized agents also produce improvements in success of up to 8.8% that generalize across users.
AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to interoperate through a common communication protocol. The Natural Language Interaction Protocol (NLIP), developed by researchers and practitioners across companies and universities and standardized by Ecma International, addresses this need by defining a standards-based application-layer protocol for AI-agent interaction. NLIP provides a lightweight semantic message envelope that can be carried over existing transports such as HTTP/HTTPS, WebSocket, and AMQP, while allowing NLIP-aware agents and gateways to adapt between clients, agents, local context stores, ontologies, tools, enterprise services, and heterogeneous underlying protocols. This paper presents the motivation and design rationale of NLIP, its message model and transport bindings, security-by-design considerations, reference implementation, representative applications, adoption signals, and relationship to emerging agent protocols such as MCP and A2A.
Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-evolution methods iteratively synthesize environments near the model's learnable frontier based on weaknesses exposed during rollouts. However, their dependence on on-policy rollouts limits generalization and the continuous provision of learning signals as the model becomes stronger. In this paper, we propose environment evolution, which incrementally increases environment difficulty off-policy and schedules the evolved environments generation by generation during training to provide continuous learning signals. We derive three evolution directions that influence environment difficulty from the multi-turn learning objective and then implement evolution along these directions through a loop-engineered multi-agent harness. Quantitative rollout experiments with Hy4 preview, Claude Opus 5, and GPT-5.6 Sol show that environment evolution consistently produces more difficult environments. We validate its effectiveness on Qwen3.6-27B and Qwen3.6-35B-A3B through simple long-horizon RL training, improving their performance by 14.4 and 18.0 percentage points on Terminal-Bench 2.1, respectively.
Zhi-Yuan Fan, Ting-Hao Yu, Yuan-Jun Cai et al.· 0 citations
Large language models are increasingly used to support organizational decisions, yet users often lack a principled basis for assessing whether to rely on a specific recommendation. Existing approaches typically evaluate broad model properties, such as reliability, uncertainty, or robustness, or focus on user trust, rather than the underlying basis for relying on an individual recommendation. Adapting theoretical foundations from epistemology, we introduce epistemic warrant, a decision-level construct that characterizes the stability of a model's preference and the scope over which that preference holds. We operationalize this construct through a four-tier reliance certificate for pairwise recommendations, distinguishing among unstable, context-dependent, locally supported, and broadly supported recommendations. We validate the construct using contemporary methodologies: known-groups tests successfully recover expert-prespecified warrant orderings, and stronger warrants systematically align with independent consensus from crowd workers. Furthermore, we demonstrate that epistemic warrant provides information distinct from verbalized confidence and is not readily explained by decision difficulty. Ultimately, this framework offers a theoretically grounded, implementable approach for characterizing the warrant of individual LLM recommendations when objective ground truth is unavailable.
Shai Vardi, Jo\~ao Sedoc· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially its decay and write-strength gates -- on the intuition that errors in a recurrence accumulate over long contexts. We test that intuition by building Minima: NVFP4 W4A4 on all 496 linear layers, GDN included. Across perplexity at 4K/32K, MMLU-Pro, GSM8K, AIME'25, GPQA-Diamond, LiveCodeBench, and RULER retrieval to 64K, Minima matches BF16 within seed noise (5-task average -0.52) while being the smallest (17.5 GiB) and fastest-prefill (+14-19%) recipe we compare, and its 32K perplexity gap shrinks with position. A four-part mechanism study explains why: (i) NVFP4's 16-element block scaling localizes the residual stream's extreme outliers, equalizing activation error across layer roles; (ii) the supposedly fragile gate projections are the least sensitive -- softplus/exponential and sigmoid parameterizations compress ~11% GEMM error to ~2% output error; (iii) the delta-rule recurrence holds injected noise at a flat plateau over 32K tokens and forgets a state impulse within hundreds of steps, because each write overwrites the state along the current key direction; (iv) the per-token quantization cost washes out with context instead of compounding. We also repair a global-scale mismatch that arises when per-module-calibrated NVFP4 checkpoints are served by kernels that fuse those modules into one GEMM, and show calibrated FP8 KV-cache scales are performance-free. The result: a practical recipe -- quantize everything, ship KV scales -- and a mechanistic account of why the recurrent half of a hybrid LLM is the easy half to quantize. Checkpoint: https://huggingface.co/minima-ai/mnma_qwen3.8_27b_nvfp4
Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored once per trajectory, but a single scalar is a poor signal across tens of steps. We propose DRACO: Distributing Rubric-based Advantage for Credit Optimization. It generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to produce differentiated per-step advantages in GRPO. The redistribution is closed-form and does not introduce any trained attribution module. On AppWorld, DRACO gains 15.9 points over the base model and 5.3 points over GRPO trained with a sparse ground-truth reward, despite not using any verifiers itself. On out-of-domain Tau-Bench, it gains 5.3 points over the base model even without a frontier judge, beating both ground-truth-reward training and other rubric-based training settings. The code for DRACO is available at https://github.com/IBM/draco.
Shubham Gandhi, Saurabh Goyal, Kiran Kate et al.· 0 citations
Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage estimator assigns each rollout a magnitude from within-group reward statistics. In the common case, this magnitude rewards rollouts that reach the correct answer through reasoning. Yet, an overlooked case shares the same surface: a rollout may land on it by guessing, and the formula still assigns a high magnitude, which we identify as the spurious advantage. This arises in three cases: bounded-answer tasks with a small candidate set; open-answer sets hosting bounded sub-cases; and search agents whose budget opens many paths to the same answer. In all three, this misleads the policy toward guess-like behaviors. We propose SIGNBALANCE, whose magnitude is composition-free: it keeps the verifier sign, uses a global scale, and restores zero-mean balance via a stop-gradient per-class rescaling. Across math and search agent benchmarks at different scales, SIGNBALANCE matches GRPO on open-answer math and improves on bounded-answer math and search agents. Code will be released.
Jiamian Wang, Samyadeep Basu, Koustava Goswami et al.· 0 citations
IRWOZ has improved industrial human-robot interaction (HRI) dialogue systems through domain-specific annotations. However, its initial version contains substantial noise in dialogue states and utterances, limiting state-tracking accuracy. We introduce IRWOZ 2.0, which addresses these limitations through large language model (LLM) enhanced generation (Mistral/Claude-3.5) and quality refinements. Our improved dataset expands to 390 dialogues across 4 industrial domains (Assembly, Delivery, Position, Relocation), featuring manual corrections and automated typo removal. Benchmark experiments on dialogue state tracking demonstrate significant improvements, with GPT-2's BLEU-4 score increasing from 0.1651 to 0.5604 compared to original IRWOZ. To support industrial HRI research, we publicly released IRWOZ 2.0 dataset at https://ieee-dataport.org/documents/irwoz-20-large-language-model-driven-dialogue-dataset-industrial-robot-conversations
Procedural instruction following is a basic requirement for controllable language-model systems, especially when generated trajectories are inspected or repaired downstream. We introduce instruction duplication, a minimal black-box inference-time control that repeats only the procedural instruction, without retraining or decoding changes. Across seven instruction-tuned models, 300 medical multiple-choice questions, eight placement conditions, and 16,800 scheduled generations, moving from one to two copies raises the deterministic All-8 diagnostic--responses passing all eight observable tests--from 90.22% to 93.17% (+2.95 percentage points), eliminating 30.2% of the failures remaining after one copy. Pre-provisional TF-IDF recall rises from 73.44% to 74.81% (+1.38 points; Holm-adjusted p < .001), while final-answer accuracy remains exactly 60.21%. Premature commitment increases from 1.52% to 2.30% (p_Holm = .00536). A blinded challenge audit yields 10/30 directional confirmations, 20/30 perceptual ties, and no reversals; its prespecified 28/30 confirmation criterion is not met. Yet this distinction can matter operationally when a downstream system acts on the generated trajectory. In Answer Engineering (AE), where explicit trajectory state determines local repair, the published reason-first no-editing SSNHL endpoint was 25.1%; system-only AE was later reproduced at 84.2%, and the same trailing duplicate raised it to 97.1%. For conductive diagnostic branch preservation, the corresponding values are 58.9% published without editing, 78.6% with reproduced AE, and 73.8% with AE plus duplication--a within-AE decrease, but still 14.9 points above the no-editing baseline. Instruction duplication is therefore a low-complexity, placement-sensitive control whose practical value can emerge through the downstream system that consumes the exposed trajectory.
Victor Lavrenko (PeaceTech VC, Israel)· 0 citations
Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.
Yalun Wu, Junfeng Fang, Jiawei Wang et al.· 0 citations
For trained operators, gauge reading requires little specialized knowledge, low cognitive effort, and high repeatability. Yet Multimodal Large Language Models (MLLMs) remain unreliable in continuous-valued measurement despite strong results on general multimodal benchmarks. Existing benchmarks expose this weakness but isolate measurement from realistic, knowledge-grounded settings, with limited situated context, specialized instruments, real-world noise, and matched diagnostic annotations, reducing realism and constraining root-cause analysis. We introduce InSituMeasure to evaluate situated measurement grounding. It contains 2,922 real industrial monitoring scenes across eight functional categories of professional engineering instruments, with dense gauge-attribute annotations and noise tags for failure diagnosis. We define metrics for numerical accuracy under predefined tolerances and unit consistency, rejection of fake or unanswerable tasks, and alignment between model failures and annotated error factors. Across 24 state-of-the-art MLLMs, the best model reaches only 25.7\% joint value-unit accuracy and 51.8\% confidence-diagnosis F1, revealing a substantial gap between general multimodal competence and reliable situated measurement. Further analysis identifies failures from text-induced shortcuts, overconfident responses, and authentic industrial noise, including mixed disturbances, viewpoint deviation, occlusion, and environmental interference.
Chao Shen, Xinyuan Li, Yunfan Zhou et al.· 0 citations
Early screening of chronic kidney disease (CKD) is critical for timely intervention, yet most machine learning (ML) and deep learning (DL) approaches require labeled data and model training, limiting their use in real-world screening settings. This study evaluates the effectiveness of large language models (LLMs) for CKD screening under zero-shot and few-shot in-context learning settings and compares them with traditional ML and DL methods. We propose a framework that uses clinically selected tabular features and structured prompt templates to enable LLM-based inference without task-specific training. LLM performance is evaluated across multiple prompt styles, feature configurations, and data settings, and compared with standard ML, DL, and tabular foundation model (TFM) baselines, and existing CKD screening tools. The results show that LLMs can achieve competitive performance using only a small number of examples, often matching or outperforming traditional approaches in low-data settings. However, their performance remains model-dependent and less stable as input complexity increases. In contrast, ML, DL, and TFM models show more consistent improvement with larger training data. Overall, the findings highlight a trade-off between data efficiency and stability, suggesting that LLMs may serve as a flexible complementary approach for CKD screening when labeled data are limited.
