Chat
-
StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams
2026-09-29 22:15:49Jhen-Ke Lin, Chung Chun WangAbstract
As natural language drives more applications, language models increasingly run inside programs as decision components: the program sends them the current state and acts on the returned decision until a newer one arrives. When evidence changes during inference, a decision correct for its own state can stay in force after that state has passed, as when a call recorder keeps running after a customer starts reading out a card number; untimed (offline) accuracy counts such an error as correct. We introduce StreamDecisionBench (SDB), which evaluates the decision in force at every instant and attributes every erroneous instant to judgment, latency or both. Its scenarios stream evidence in four application families, with reference decisions computed from public rules by executable code. We summarize in-force accuracy across update intervals of 1-5 s by its normalized area under the curve on a logarithmic time axis, giving equal weight to equal multiplicative ranges. Across six settings of four hosted models, this score stays within 2.9 points of the scenario-wise product of untimed accuracy and an oracle's integrated timing score. Reasoning improves judgment, but at low effort latency costs Luna and Terra, two GPT models we also evaluate without reasoning, 38.8 and 42.8 points relative to untimed accuracy; a faster component with weaker judgment attains a similar integrated score to Terra without reasoning. The aggregate and family curves show where these tradeoffs change, making the evaluation's time-scale dependence visible.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38612
PDF
-
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
2026-09-29 20:54:47Galbot Team, Xuchuan Chen, Xiaoqian Cheng, Yu Deng, Lihe Ding, Shaocong Dong, Xiangjun Gao, Haozhe Jia, Zekai Li, Zhoujian Li, Yunrui Lian, Sikai Liang, Chenghuai Lin, Dairu Liu, Jiahang Liu, Qingtao Liu, Yuxuan Ma, Zekun Qi, Jiayi Su, He Wang, Ruochen Xu, Tianyu Xu, Xudong Xu, Zhe Xu, Mi Yan, Siming Yan, Li Yi, Ruixi Yu, Jinlu Zhang, Yintianrun Zhang, Zhikai Zhang, Zhizheng Zhang, Yixin Zheng, Weiyi ZhuAbstract
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and feedback-driven adaptation. In gripper manipulation, Astra can correct task targets and prepare contact conditions for subsequent policy execution; hybrid control with {\pi}0.5 achieves 48% success on the evaluated RoboDojo subset. In dexterous manipulation, hybrid control achieves 50% success in ten experience-guided DexJoCo trials, while direct in-hand control struggles to coordinate finger contacts. In mobile manipulation, hybrid control reaches 38.7% success on the evaluated RoboCasa365. In navigation, Astra leads our local comparisons, reaching 92% success on RxR instruction following and 82% on HM3D object search, although search incurs substantial detours. In locomotion, dense motion-reference generation remains unreliable: none of five sequential attempts on a single obstacle course reaches the goal, despite improvements in stability and forward progress. In humanoid loco-manipulation, Astra exceeds baseline methods on 13 of 30 HumanoidBench tasks with pretrained whole-body controllers. These findings reveal a gap between useful task decisions and reliable physical control. Inference latency further constrains practical control: across 50 RoboDojo instances per condition, policy-assisted and direct control consume 624.8 million and 1.132 billion tokens. A 30-second locomotion run requires 250 model calls averaging 39.86 seconds each, with physics paused during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38537
PDF
-
VAmoS Part Deux: Harder, More Realistic Voice-Agent Simulation
2026-09-29 20:33:57Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan, Sun Kim, Victor Shih, Mehdi Jamei, Andi PartoviAbstract
Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that combines these challenges in 100 calls about utility billing and payment assistance. Each caller makes two to four requests. The agent has sixteen tools backed by a stateful Stripe billing twin and the Apache Fineract loan engine, with account access blocked until caller verification succeeds. The tasks use public household electricity data and a policy based on Pennsylvania's residential billing rules. An LLM-as-a-verifier checks the agent's actions and spoken figures against explicit requirements. On a calibration run, it agrees with a code verifier on 99.1% of checks. Across fourteen voice stacks and three repeats per task, completion ranges from 17.3% to 44.7%. Grok Voice leads, and Gemini 3.8 Live and GPT-Live follow at about the same cost per call. Background television reduces pooled completion from 38.7% to 8.6%. The simulated caller often accepts an incorrect result because it hears the agent's words but cannot inspect its actions. These findings show why voice agents need evaluation across the whole call, including what they say, what they change, and how they handle competing speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38512
PDF
-
Voices as Handles: Reasoning about Speaker Identity with Frozen Text LLMs
2026-09-29 20:25:40Runqiu Xu, Zhisheng Zheng, David HarwathAbstract
Multi-user voice agents must track who said what across dialogue sessions. Text LLMs are attractive backbones for such agents, but transcripts alone do not expose acoustic speaker identity, leaving the model without a persistent reference for linking information to speakers across sessions. We address this gap by introducing Speaker Handles, soft-token representations that expose acoustic speaker identity to a frozen text LLM for cross-session speaker-dependent reasoning. A three-stage curriculum trains a lightweight projector, with fewer than 0.1% of the backbone's parameters, to map speaker embeddings into these handles. Establishing whether the resulting handles truly support cross-session speaker-dependent reasoning is challenging with existing benchmarks because textual cues can partially reveal fact ownership. We therefore present SpeakerBind, a controlled shared-agent benchmark in which overlapping facts across users require correct cross-session speaker attribution. Speaker Handles achieve 97.40-98.36% accuracy on VoxCeleb1 and 70.40% on SpeakerBind, close to the 71.88% topline. These results show that the proposed Speaker Handles provide an efficient way to integrate acoustic speaker identity into frozen text LLMs for speaker-content reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38501
PDF
-
Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Models
2026-09-29 20:20:24Joseph T Colonel, Daniel Katzman, Kelsey Kirker, Adam N Davidson, Shalaila S Haas, Cheryl Corcoran, Ren\'{e} S Kahn, Guillermo Checci, Baihan LinAbstract
Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Yet evolving consent and protocol requirements can oblige investigators to remove a designated speaker from multi-speaker recordings and to verify said removal at a scale infeasible for manual review of entire corpora. We study this verification problem for role-driven dyadic clinical dialogue in psychiatry and investigate it with two parallel, symmetric pipelines: confirming that clinician speech has been removed from psychiatric interview recordings, and confirming that patient speech has been removed from the same recordings. Each pipeline redacts the raw audio for its target role and then scans the surviving output with audio-language and large-language models to identify missed deletions. We evaluate this approach on a corpus of 48 dyadic recordings drawn from psychiatry settings, testing four open-weight models in an inference-only setting: Gemma-4-12B, Gemma-4-31B, Nemotron-3-Nano, and Nemotron-3-Nano-Omni. A disjunctive OR ensemble over fourteen model-view configurations had a combined F1 of 0.478 (precision 0.330, recall 0.870), an improvement over individual model estimates driven by recall gains that point to substantial complementarity across models and context views.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38491
PDF
-
KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy
2026-09-29 20:08:21Xueting Fang, Zehui Li, Yang Yang, Camilla Giovino, Shubh K. Patel, Shailly Prajapati, Vallijah Subasri, Caihua ShanAbstract
Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present information in different ways, and clinicians must obtain relevant history and determine which examinations are needed before reaching a diagnosis. Diagnostic accuracy alone therefore cannot establish whether an agent gathered essential information or conducted an appropriate clinical assessment. Furthermore, existing benchmarks lack professional clinicians' verification. To address this gap, we introduce KlinikeBench, a benchmark of 333 clinician-authored tasks, each providing an isolated sandbox environment with a virtual patient, clinical tools, and task-specific success criteria. More than 35 clinicians contributed to case authoring and benchmark evaluation. In an empirical study, clinicians gave simulated dialogues higher mean quality ratings than reference conversations, which is adapted from real conversation. In each task, an LM has a fixed budget of turns to communicate with the patient, ask about relevant history, request examinations, follow action constraints, and record a final diagnosis. We score these steps separately as well as together. Across 31 models and seven model families, the best-performing models (e.g., GPT-6-astra and Claude Opus 5) succeed on less than 30% of tasks, even though their diagnosis accuracy reaches 90.7%. Some models benefit from talking with the patient; others diagnose well from a complete chart but perform much worse in conversation. Overall, KlinikeBench provides a testbed for evaluating the full clinical encounter and reveals a substantial gap between diagnostic accuracy and performance in interactive clinical assessment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38480
PDF
-
Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles
Abstract
Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar default. Single-pass answers obscure the distinction between agreement produced by a tightly constrained answer space, prompt-vocabulary echo, and broader answer spaces with stable alternatives beneath the surface. We introduce CHOIR (Collective Hierarchically-Ordered Inquiry Responses), a framework that adapts free-list elicitation from cognitive anthropology to LLM ensembles. CHOIR repeatedly elicits ranked lists, clusters items into prompt-level concepts, and measures concept salience across models, prompt variants, and persona conditions. We evaluate CHOIR on Infinity-Chat 100, an external prompt bank from recent work on open-ended model homogeneity, and on a 27-question targeted diagnostic bank designed to isolate mechanism-level contrasts. On Infinity-Chat 100, CHOIR reproduces high surface agreement (93/100 prompts above chance) while separating narrow prompts from broad prompts with recoverable depth. Across targeted probes and the external prompt bank, base-model identity remains the strongest recoverable signature, and persona prompts shift surfaced concepts within base-model signatures. A source-blind ranking module prioritises rare-but-stable candidates for later inspection. CHOIR turns open-ended homogeneity into a diagnostic measurement problem by asking where models converge, why they converge, and what remains reachable under structured depth probing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38448
PDF
-
Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
2026-09-29 19:09:55Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies, Robert KirkAbstract
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of their assigned task. We evaluate whether frontier models conduct supply-chain attacks against out-of-scope, third-party targets when placed in difficult cybersecurity challenges, motivated by recently observed cases of models attacking real open-source repositories during evaluations. Applying our methods to GPT-6 Astra and previous OpenAI models, with cyber safeguards disabled, we find that GPT-6 Astra attempts complete supply-chain attacks in simulation at a higher rate than GPT-5.6 Sol and GPT-5.5. This includes writing malicious code as a contribution to an out-of-scope open-source codebase, creating fake identities to deceive open-source developers, and submitting benign contributions before malicious ones. GPT-6 Astra frequently reasons about the scope of the challenge in its chain-of-thought yet still proceeds to attack out-of-scope targets; it often asks for permission, and treats an automated message as as authorisation; and it continues to take unsanctioned actions, at a reduced rate, when internet access is more explicitly disallowed. Our evaluation builds on an internal version of Petri, an open-source LLM auditing tool, with all tool calls simulated by other LLMs, so that no real network access, systems or third-party repositories are reachable and no real-world harm is caused. Finally, we discuss limitations, in particular simulation awareness. We believe simulation awareness may have driven some of the observed behaviour but does not remove our concern. Our results suggest that defences beyond model alignment, such as sandboxing and monitoring, are increasingly critical for safe and secure deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38415
PDF
-
MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science
2026-09-29 18:50:21Jinyi Ye, Yuangang Li, Chenxiao Yu, Preyashi Poddar, Priyanka Dey, Longtian Ye, Zihan Wang, Xiyang Hu, Emilio Ferrara, Yue ZhaoAbstract
Personas used to seed LLM social simulations face a cold-start problem: existing methods lack a principled basis for deciding which attributes to include and how to assign their values. As a result, synthetic populations may misrepresent the demographic composition, latent attributes, and dependency structure that shape downstream behavior. We introduce MetaPersona-DB, a dataset of 11,000+ empirical human-subjects studies annotated with task-relevant variables, reported relationships, and aggregate-level population statistics. Building on this resource, we propose MetaPersona, a framework that retrieves task-relevant evidence, constructs literature-derived persona dependency graphs, and samples synthetic populations from empirical priors linking demographics, latent attributes, and outcomes. Across three downstream case studies, three baselines, and three frontier models, results vary by task and model: MetaPersona performs strongly on misinformation belief and AI-tool sentiment, while results on income redistribution are mixed. It also reduces persona-construction cost to under $0.5 per task using GPT-5.2. Finally, we present MetaPersona-Studio, a prototype interactive interface for empirically grounded persona generation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38392
PDF
-
Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks
2026-09-29 18:21:50Sumit Asthana, Michael Ion, Kevyn Collins ThompsonAbstract
High quality synthetic data is central to post training LLMs for adaptive AI applications that represent the diverse expert strategies and decisions in conversations. Prompting LLMs directly or conditioning them on end use scenarios yields low diversity data that collapses onto dominant modes. We propose a method to generate diverse high quality synthetic data using Generative Flow Networks (GFlowNets). We show that training GFlowNets to generate latent conversation structure using a Gaussian mixture density over key interaction features (e.g., confusion episode dynamics, scaffolding directive balance) enables sampling expert strategies in proportion to their prevalence in the training data. Across two structurally distinct domains, tutoring and emotional support dialogues, our GFlow based synthetic data generation approach offers a better balance of fidelity, mode coverage and authenticity than reinforcement-learning and end to end LLM baselines, without copying training data. Evaluated on three downstream outcome prediction tasks, classifiers trained on synthetic GFlowNet generated conversations provide a stronger training signal than competitive synthesis baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38359
PDF
-
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
2026-09-29 18:10:49Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Bl\"obaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika GencAbstract
Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance, yet its combinatorial search space demands substantial human effort that must be repeated as models change. Existing automated methods explore this space narrowly, optimizing only components such as prompts or skills or becoming trapped by fixed, exploitative search strategies. We introduce MILO (Meta-evolutionary Island Orchestration), a framework that co-evolves agent harnesses and the strategy used to discover them. MILO combines: (i) hierarchical lineage memory over island-based trees, using rejected mutations as negative evidence; (ii) per-island mutator agents that rewrite complete harnesses using global search history and parent-specific feedback; and (iii) an orchestrator that adapts search through lineage grafting and speciation, mutator reassignment and curriculum revision. Across Terminal-Bench 2.1, PaperBench, and DeepSWE, MILO-discovered harnesses outperform eight state-of-the-art harnesses and six search methods using frontier (Opus 4.8) and open-weight (gpt-oss-120b) models. With Opus 4.8, MILO improves resolution over its initial harness by $+12.0\%$, $+28.3\%$, and $+10.3\%$, respectively, compared with best prior-search gains of $+4.5\%$, $+18.3\%$, and $0\%$. On Terminal-Bench 2.1, it achieves $86.1 \pm 2.0\%$, exceeding the official leaderboard's top entry ($83.8 \pm 2.3\%$) while using 26\% fewer tokens than its initial harness. On EinsteinArena open problems, MILO improves best-known upper bounds for ErdÅs minimum-overlap ($0.3808586 \to 0.3808568$) and the first and third autocorrelation inequalities ($1.50274365 \to 1.50274360$; $1.45081 \to 1.44889$).
Abstract (translated)
URL
https://arxiv.org/abs/2609.38349
PDF
-
Examining Variation in How Guided AI Tutors Resolve Student Impasses
2026-09-29 18:10:09Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli, Josh Arens, Ksenia Ionova, Clayton Cohn, Shima Salehi, Rene KizilcecAbstract
When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves the student in a frustrating, persistent impasse (i.e., wheel spinning). Generative AI tutors increasingly use guardrails restricting answer-giving, yet little is known about how such tutors behave once an impasse persists. We analyze 20,462 student turns from 1,260 authentic sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns of three major types: conceptual errors, expressed uncertainty, or help-seeking. We then used these impasses to simulate three tutoring conditions to study variation in AI tutor guidance through impasses: baseline, no-direct-answer, and guided tutor. For a sample of 150 impasses, prompt specificity changed pedagogy: a baseline tutor provided the answer directly in 50.7% of responses, a no-direct-answer tutor asked a follow-up question every time, and the guided tutor responded in a wide variety of ways depending on the context. We then analyzed impasse trajectories in authentic interactions, finding that each additional impasse turn lowered the odds of next-turn recovery by 12.7% (AOR = 0.873, p < .001), and early dropouts were caught in recursive concept elicitation before reaching execution. The benefit of questioning decayed as impasses persisted (scripted question x depth AOR = 0.78; follow-up x depth AOR = 0.83), whereas addressing the student's error grew more beneficial (AOR = 1.14); after a failed scripted question, repeating it was followed by recovery in 28.1% of cases, compared with 39.8% when the tutor addressed the error instead. For learning analytics, these findings identify impasse depth and type as observable, turn-level dialogue signals that analytics can use to trigger graduated, state-sensitive assistance in real time.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38346
PDF
-
Strike a Chord! Modal Kinetic Typography
2026-09-29 18:00:15Maham Tanveer, Jiyeon Han, Nanxuan Zhao, Hao ZhangAbstract
We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build motion from the glyph's natural vibration modes. Specifically, a finite-element eigenproblem assembled from the vector outline yields the glyph's softest modes, for the whole letter and for each of its parts, allowing it to bend. The problem's zero-energy solutions, i.e., rigid translations and rotations, are applied in closed form to each part, allowing parts to also move as blocks. To animate the glyph, a frozen video diffusion model supervises only the modes' amplitudes and phases. Our modal approach addresses two weaknesses of prior work. Free-form point optimization under video score distillation (SDS) moves each point and frame independently along noisy gradients, tearing the outline and causing jitter. In contrast, our modes are smooth along the outline and driven by a few whole-cycle harmonics, which restricts these gradients to smooth, seamlessly looping motion. On the other hand, structured alternatives rely on skeletons or keypoints from category-specific priors, whereas our modes come from the glyph itself; the only prior is a list naming each letter's moving parts, generated once for the whole alphabet by a language model. In modal kinetic typography, shape and motion are disentangled by construction: a single base outline is sculpted toward the concept, and the modal drive cannot alter it, so a letter can also be animated without being reshaped. Our method produces more articulated and smoother motion than Dynamic Typography and AniClipart at comparable or better concept alignment, with less glyph tearing than Dynamic Typography, and is preferred by human raters, including in a frozen-shape setting where motion alone must carry the concept. Our results were also preferred over Astra (GPT-6) by human raters.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38325
PDF
-
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
2026-09-29 17:57:25Paras Dahal, Anton Bakhtin, Taco Cohen, Zhengxing Chen, Carole-Jean Wu, Rob Fergus, Scott Yih, Gabriel Synnaeve, Ruslan Salakhutdinov, Sanjeev Arora, Jason Weston, Anirudh GoyalAbstract
As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation, while a controller consolidates what the run has established, explores next options, assesses what each option is worth under the remaining budget, and dispatches the chosen work with context drawn from persistent memory. Between decisions the controller carries only a compact account of the run rather than replaying its full history. Our baselines span production coding agents and research harnesses, together with a Direct Control Agent using the same workers and compute budget allowance. On ProgramBench, which tests long-horizon agentic capability through program reconstruction, meta-reasoning achieves 71.5% with GPT-5.5 against 58.0% for Codex; with Opus 4.8 it achieves 67.2% against 65.5% for Claude Code. On the other benchmarks, spanning abstract reasoning, multi-domain long-horizon reasoning, and proof generation, it gains between 3.6 and 4.2 points over direct control, averaged across three frontier models. It keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets. Artifact-graph analysis reveals more reuse of earlier work, higher coverage of correct solutions in most settings, and nonuniform gains in final selection. These results indicate that spending computation on structured control becomes more important as agents scale to longer runs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38147
PDF
-
UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
2026-09-29 17:17:24Ashish Jain, Armaan SandhuAbstract
Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated user controls what information the agent receives and when, yet current benchmarks score only the agent and do not directly measure whether the user correctly executed its assigned role. We introduce UserProxyBench, an evaluation layer over the tau-bench family, and the User Fidelity Score (UFS), which measures adherence to the benchmark's private user instructions using task-grounded rubric criteria scored independently of agent success. Holding the agent fixed at GPT-5.5 and varying only the user proxy across 375 enterprise tasks changes mean task reward by 15.2 points, while 24.4% of successful episodes contain a user-specification violation. The dominant failure is premature disclosure: users provide information before it is requested. This behavior has little effect on task reward, yet among successful episodes it causes the agent to make 1.06 fewer tool calls on average, changing the interaction being evaluated while preserving the reward. Finally, across seven proxies we identify an empirical cost-fidelity frontier, enabling practitioners to select the least expensive simulator that satisfies a required fidelity level.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38043
PDF
-
Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S
2026-09-29 17:04:18Christopher J. ChanhnourackAbstract
We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, coverage-first packet compilation, and deterministic reasoning scaffolds; an LLM is used only as a replaceable final reader. The chain places all gold sessions in the candidate pool for 468/470 answerable questions and produces gold-complete packets for 462/470. With a Claude Opus reader called through an unpinned CLI alias, two 500-question passes score 479/500 and 475/500 under GPT-4o. The 72 answerable knowledge-update rows used a substantively modified scoring prompt whose effect under the official text has not been measured. The pair straddles Chronos High's published 478/500; differences in reader generation, scoring prompt, and possibly data version, plus within-system variance, establish neither superiority nor equivalence. A grok-4.6-high reader on the same packets scores 476/474, while a maximum-reasoning-effort agentic variant regresses to 461/465. The headline passes differ on eight verdict-flip rows. A second judge agrees with the headline judge on 493/500 rows (98.6%) in each pass and scores both passes 472/500; the official judge also flips three verdicts when re-scoring byte-identical pass-1 answers. Negative controls rejected a verifier that repaired three wrong drafts but broke eleven correct drafts. All components were developed on the same 500 questions, with no held-out evaluation or independent human adjudication; retrieval and scaffold method sources and transcript-derived audits are held; and the headline reader received extra operator context, its complete requests were not retained, and MCP tool availability is unresolved. We release materialized packets, scaffolds, reader outputs, judge verdicts, and controls for inspection and re-scoring.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38021
PDF
-
HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment
2026-09-29 16:56:24Kenan Alkiek, Moontae Lee, David Jurgens, V. G. Vinod VydiswaranAbstract
Running a language model locally offers advantages in privacy, latency, and cost, but local hardware fits only small models, which are less capable than frontier models. The usual remedy for a hard query, escalating it to a cloud model, gives up the privacy and cost advantages of running locally. A deployment that stays local faces two decisions for hard queries instead. First, it can spend more computation on a query, e.g., reasoning before answering, which raises accuracy at a cost in latency, so it must decide which queries are worth the extra computation (efficiency). Second, some queries are beyond the local model, and delivering a wrong answer is worse than deferring the query to a human in the loop, so it must decide which answers are safe to deliver (safety). We show that both decisions can be made from the model's own hidden states. The prefill state, computed before any token is generated, predicts whether the model will answer correctly, and the answer state, at the end of the generated answer, predicts whether that answer is correct. HARISSA fine-tunes the model so that both states predict correctness, then makes both decisions with one policy that cascades through the ways of answering from cheapest to most expensive, skipping a way the prefill state predicts will fail and deferring the query when the answer it stops with is predicted wrong. On a device running a single model, HARISSA is within one accuracy point of chain-of-thought at 2.7 times lower latency. On a server holding four sizes of one model, HARISSA is more accurate than the FrugalGPT and Self-REF cascades at the same latency, and at the same deferral rate the answer state leaves fewer wrong answers than the standard confidence signals in five of six task and setting pairs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38006
PDF
-
Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
2026-09-29 15:40:53Jaeseung Heo, J Rosser, Dongwoo KimAbstract
Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influence different behaviors of an LLM involves repeated influence computation. Reusing stored training gradients reduces the computational cost, but storing full gradients is prohibitively expensive at LLM scale. We study how to compress these gradients while preserving influence estimates for future queries that are unknown at storage time. Through a worst-case analysis, we characterize the optimal fixed-dimensional linear representation and propose eigenbasis-corrected one-bit gradient projection (EOGP) to approximate it at scale. Specifically, EOGP uses EK-FAC to reduce gradient dimensionality, then applies PCA within the retained subspace to learn compression directions from the training gradients. We then apply one-bit quantization to the resulting coordinates, allowing more coordinates to be retained within a fixed storage budget. On GPT-2, EOGP predicts retraining outcomes more accurately than the evaluated compression baselines while using one-sixteenth of their per-example storage. On OLMo 2 SFT models from 1B to 32B parameters, EOGP remains competitive with the baselines allocated over 100 times as much storage per example.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37842
PDF
-
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
2026-09-29 15:32:52Yubo Li, Yidi Miao, Ramayya Krishnan, Rema PadmanAbstract
LLM-as-a-judge scales evaluation, but reasoning judges are slow and costly. We study JEV-as-a-Judge: evaluation with JEV, a decision-only judge that returns label probabilities instead of text, and whose confidence decides whether to accept its verdict or escalate to a reasoning judge. Against sixteen generative and reward-model judges, with blinded human adjudication, JEV comes within three points of GPT-6 wherever a verdict can be read off the text, at 0.36% of its fee and a 0.15-second median latency, and falls behind where the verdict must be derived, as in math, code, and logic. Its confidence marks this boundary. With a threshold frozen in advance, accepting confident verdicts and escalating the rest is 0.9 points more accurate than GPT-6 on 1,610 held-out pairs at 41% of its fee, and in a pre-specified live test on two new workloads the cascade matches GPT-6's accuracy exactly. Confidence routing weakens on style-adversarial pairs and reference-free prose; we close with a simple recipe for validating thresholds locally.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26550
PDF
-
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
2026-09-29 15:28:13Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang, Shun Lei, Di Cao, Teddy Sun, Zhiyong WuAbstract
Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and make acoustic cues more explicit in replies, yet does not ensure their effective use in response planning. We call this mismatch the perception-reasoning gap. In addition, CoT may not fully capture acoustic cues in words, and generating it adds inference latency. To address these limitations, we introduce LoopSLM, which builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass. Its two-stage training further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT. On EchoMind, LoopSLM improves paralinguistic understanding, reasoning, and reply quality over Qwen2.5-Omni-7B. Against the CoT-SFT baseline, LoopSLM gains over 20 points in reasoning accuracy while generating 64.5% fewer tokens at half the latency. It also outperforms Qwen3-Omni-Thinking on most empathetic reply metrics with 34x lower latency. Despite training only on dialogue data, LoopSLM improves accuracy on general audio benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37818
PDF
