Chat
-
Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge
2026-10-06 16:57:47Chuhong Xu (Sofia University), Bo Su (Indiana University), Ziyao Chen (University of California, San Diego), Ruiyang Xu (Northeastern University), Shimeng Dai (Michigan State University), Xinyu Qiu (Northeastern University)Abstract
Financial reports repeat values across periods, metrics and accounting lines, allowing an LLM-generated calculation to be numerically correct while citing the wrong financial role. We evaluate what probabilistic evidence verification adds beyond number matching using Jev as a source-support verifier for GPT-4.1-mini calculation traces. A signed-number-at-pointer baseline explains most recovery over exact quotation checks. To isolate the remaining role-recognition problem, we hold operands and arithmetic fixed, move citations between same-number cells, and retain controls that express equivalent facts. These contrasts reveal both wrong-role citations that pass and valid alternative citations that are withheld. Explicit column labels improve selected wrong-role decisions while also lowering support for some equivalent evidence. A constructed follow-up on 36 new source pages, labeled by a non-author reviewer, extends this evaluation and exposes the same tradeoff between detecting role errors and retaining valid citations. The contribution is a controlled evaluation that identifies what a probabilistic financial verifier distinguishes when numerical matching is held fixed. For LLM-based financial assistants, it makes numerical correctness, cited-role support and acceptance outcomes separately assessable.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08675
PDF
-
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
2026-10-06 16:52:23Orion Reblitz-RichardsonAbstract
Language models increasingly act as agents. An agent that says an action is wrong and then takes it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We build a pre-registered panel of 248 scenarios across five kinds of pressure. Each scenario is posed twice to the same model, once as the agent choosing what to do and once in the third person asking which option is right, so the model's own judgment is the reference. Every scenario has a twin with the pressure removed, and every model gets a positive control in which its operator orders the violating action, so that a missing gap can be told apart from a blind instrument. On OLMo-3-7B-Instruct, the model takes the action it judged wrong on about one in five pressuring scenarios, more often than on the same scenarios with the pressure removed. Across four instruct models the gap depends on the post-training recipe: OLMo-3 and Meta's Llama-3.1-8B-Instruct carry it; Tulu 3 shows none on the whole panel (above about 0.01 in probability) or on its own most-pressuring scenarios; Qwen2.5-7B-Instruct shows none on the whole panel (above about 0.02) and is unresolved on its own (0.083, -0.028 to 0.195). Meta's recipe and Ai2's Tulu 3 start from the same Llama-3.1 weights, and only Meta's carries the gap. Reading a chat model outside its chat template reverses the sign of its gap with nothing at stake (-0.038 against +0.055 under the template on OLMo-3), a distortion present on two of three recipes. On both models that carry it, reasoning about the stakes before acting moves the choice back toward the model's own judgment, against a same-length non-moral task, with or without the pressure; on OLMo-3, naming the norm at stake does about a third of that. The gap is a measurable target for post-training recipes, not a fixed property of pretrained weights.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08670
PDF
-
Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics
2026-10-06 16:44:02Mariya Miteva, Maria Nisheva-PavlovaAbstract
Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidence. We developed a neuro-semantic verification framework that converts radiomic measurements into addressable evidence records and machine-checkable claims. Methods: UPenn-GBM radiomics were aligned with de novo CaPTk extraction from standardized MRI and expert-validated segmentations in an independent multicenter cohort. The shared space comprised 1,728 features from T1, T1GD, T2, and FLAIR MRI across three tumor regions. Reference-defined semantic states were derived from 611 UPenn cases. We evaluated cross-cohort transportability, model-linked provenance, deterministic verification, controlled predictive degradation, and an LLM claim-extraction pilot; MGMT prediction served only as a transport stress test. Results: Median semantic-state agreement was 0.786 (weighted kappa 0.709), ranging from 0.918 for morphologic to 0.252 for intensity features. The external evidence ledger contained 1,655 model-linked records for 331 patients. The verifier achieved 100% exact-set accuracy in a 6,620-claim corruption benchmark. In a 24-case pilot, GPT-5.6 Sol reproduced 72/72 prespecified atomic claims, and the frozen verifier recovered 24/24 expected conditions. During controlled degradation, ROC AUC declined from 0.899 to 0.500 while verification accuracy remained 1.000. External MGMT discrimination was weak (ROC AUC 0.543). Conclusions: Verifiability can be engineered and evaluated independently of predictive performance. LLMs may structure explanations, while final evidence-consistency checking remains deterministic.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08660
PDF
-
Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents
2026-10-06 16:10:43Mohamed Chenene, Carlos Rosas-Hinostroza, Anastasia Stasenko, Shani Evenstein Sigalov, Pierre-Carl LanglaisAbstract
Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right entities and properties and chains their relations. Language models offer a natural-language alternative but answer largely from memory, which is least reliable for less prominent entities. We study agents that instead answer by exploring the graph, and argue that two obstacles limit them: the lack of training data recording how a solver explores, and interfaces that add large graph results directly to the model's context. We test three hypotheses: that the difficulty of graph search can be controlled through the structure of a question rather than only through obscure entities or wording; that much of the failure on long-horizon search comes from how retrieved evidence is managed rather than from the model itself; and that, in a suitable environment, open-weight models can match commercial closed ones. We construct multi-hop questions on a frozen Wikidata snapshot by replacing named entities with nested conditions, checking after each expansion that the target remains unique and that every new condition is necessary. We release 10,235 solving traces over single-entity and multi-hop questions, together with the recursive language model (RLM) harness that produced them, in which models batch graph calls, keep results in persistent Python state and interpret selected evidence through sub-calls. On 100 questions, the harness improves both models we ran under both interfaces compared with direct tool calling over the same functions: gpt-6-luna rises from 49 to 61 correct answers, doubling its multi-hop accuracy, and Qwen3.8-27B, an open-weight model served on a single GPU, from 60 to 74.
Abstract (translated)
URL
https://arxiv.org/abs/2610.06650
PDF
-
Incidental information contaminates patient notes and disrupts clinical reasoning in large language models
2026-10-06 15:55:29Krithik Vishwanath, Brandon Ye, Anton Alyakin, John E. Markert, Aaron Hsieh, Micha{\l} Ma\'nkowski, Eric K. OermannAbstract
Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a failure mode shared between these two applications by assessing their sensitivity to information incidental to the patient encounter. In 576 patient-clinician dialogues, we found that frontier models inserted small-talk exchanges into 35% of notes, while mean quality scores changed by at most 0.20 points on five-point scales. In 3.7% of frontier notes, models misattributed the asides or used them clinically. In 57 mock recorded consultations, background speech from a separate patient encounter at -10 dB leaked into 48.2% of transcripts, with contamination detected in 5.3% of downstream notes generated by four open-weight models. We propose a dual encoding hypothesis of clinical reasoning and distraction in LLMs, with preliminary evidence that LLM components associated with disruption by incidental information also support clinical reasoning. These findings support evaluating resistance to incidental information before clinical use, with safeguards that prevent contamination while preserving clinical reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08585
PDF
-
How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing
Abstract
Probes are the workhorse of interpretability. If a model's hidden states predict a variable, the model is said to represent it. But a probe score has no fixed meaning. An $R^2$ of 0.6 may only reflect what the input already gives away, and the same score can mean different things on different data. We propose reading every probe score against two reference points: a floor, what a declared set of simple inputs already predicts, and a ceiling, what the full input can predict. The gap between them, the headroom, is the range in which a probe can show that a model computes something beyond the simple inputs. We prove that headroom vanishes in two ways: the target stops depending on a hidden variable the model must infer, or the input stops revealing it. We test this on transformers trained for in-context meta-analysis, which must infer the hidden heterogeneity between studies to weight them correctly, and where both reference points are known. Under distribution shift, probe scores fall and prediction error rises $12$--$15\times$, yet the model recovers a similar share of the headroom, indicating that the data lost information, not the representation. We then analyze the real models. The single-cell foundation model scGPT encodes biological variability only partially. We also revisit four influential LLM probing studies, which claim that models represent geography, the state of an Othello board, truth, and the demographics of their users. Against a floor computed from the input text alone, some of these claims hold, while others are largely explained by the text itself.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08544
PDF
-
Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT
2026-10-06 14:18:54Zhen Yu, Wenyang Liu, Kejun Wu, Chengwang Xiao, Renjie Qiao, Chengtao CaiAbstract
Image Bitstream Fine-grained Understanding (IBFU) aims to directly perform fine-grained classification and semantic description generation from encoded image byte sequences. In contrast to conventional pixel-domain visual understanding, IBFU conducts semantic analysis without fully decoding images into the pixel domain. Since pixel-level visual content is not explicitly reconstructed during inference, this paradigm reduces visual exposure within the processing pipeline and suits privacy-friendly Artificial Intelligence of Things (AIoT) applications. In this paper, we propose Bitstream Fine-grained Generator (BFG), a novel foundation model tailored for IBFU. BFG consists of two main components: a Bitstream Semantic Encoder (BSeE) and a Fine-grained Semantic Generator (FSeG). BSeE directly models semantic representations from encoded image bitstreams without explicit pixel reconstruction, while FSeG transforms the extracted bitstream semantics into detailed natural-language descriptions through autoregressive generation. To train BFG and comprehensively evaluate IBFU in practical AIoT scenarios, where image bitstreams may suffer corruption during transmission and storage, we construct a large-scale Corrupted-bitstream Fine-grained Understanding dataset (CFU-D), containing both intact bitstreams and corrupted variants across multiple corruption types and severity levels. Experiments show that BFG maintains stable fine-grained caption generation under bitstream corruption. For example, the performance only has slight change from 0.6339 to 0.6077 in terms of average CIDEr score on Stanford Dogs Caption dataset, while vision-language models, such as Qwen-VL-Chat, BLIP-2, GLM, Gemini, and GPT suffer severe performance decrease. This paper provides a practical paradigm for privacy-friendly fine-grained understanding in AIoT.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08414
PDF
-
Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals
2026-10-06 14:18:13Jerzy Kami\'nski, Ilya Galyukshev, Artem Kuznetsov, Danil Fedorov, Kirill Redko, Sergey Chuprin, Aidar Shumbalov, Stanislav Chumakov, Anna KalyuzhnayaAbstract
Large language models routinely answer questions that cannot be answered from the information given, and in dialogue they answer before enough has been said. Unanswerability is linearly decodable from hidden states, but it is unclear which of its forms share a representation and whether the signal is useful in dialogue. We contribute a turn-labeled multi-turn benchmark (423 conversations, 1,661 labeled turn-states) and an evaluation harness with a simulated user who answers clarifying questions, and use them with six datasets and six open-weight LLMs to test how far probes for unanswerability carry. Probes transfer robustly between datasets that share a ground of unanswerability: missing information in math (AUROC 0.77-0.97) and in a passage (SQuAD 2.0<->MuSiQue, 0.77-0.90). Probes for epistemic "known-unknowns" transfer poorly to math, but this separation weakens under lexical controls and changes with layer and coordinate system, so it remains unresolved. Single-turn probes fail zero-shot to detect when a conversation becomes answerable; in-structure probes recover it, but no better than a bag-of-words classifier. A gate on the calibrated probe, with no model fine-tuning, fires on underspecified turns far more precisely than chance, and its end-task success comes within 0.08 of a gate given the true labels. Yet across four models it does not reliably beat vanilla generation or prompted consolidation. The remaining gap lies mostly in how models use a clarification, not in detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08413
PDF
-
A Stevens's Power Law Check-up of GPT-5.5's Image-Based Visualization Reading
Abstract
We adapt Stevens's power law to measure the innate ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of algorithmic models. In our pilot study, models see no legend. A model first views a reference visual representation and estimates its magnitude, then estimates the magnitude of each subsequent image of the same representation relative to that reference. Our evaluation of twelve visual variables makes how algorithmic models read visual encodings measurable, comparable with human perception, and more interpretable to humans.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08365
PDF
-
MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
2026-10-06 12:31:05Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying ChenAbstract
Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing evaluations also lack a unified testbed for both stable client characteristics and evolving psychological dynamics. We propose MASC, a Multi-Agent Self-Calibration framework with latent construct alignment for consistent client role-playing in psychological counseling. MASC combines construct-guided generation, collaborative refinement, consistency verification, and memory-based revision in a closed calibration loop that detects and corrects inconsistencies as dialogue unfolds. We further introduce CRPC-Bench, a benchmark covering session-level profile information and Big-Five personality traits, as well as turn-level psychological state, communicative action, and emotion expression. CRPC-Bench contains 38 motivational interviewing client profiles augmented with personality and emotion annotations. Experiments show that MASC outperforms existing methods across profile, personality, receptivity, and turn-level consistency, with the heterogeneous configuration achieving the strongest overall performance. MASC and CRPC-Bench provide a unified foundation for developing and evaluating psychologically coherent client simulations for AI-assisted counseling research and training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08250
PDF
-
LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs
2026-10-06 12:27:34Andr\'{e} G. Pereira, Augusto B. Corr\^ea, Felipe Meneguzzi, Jendrik SeippAbstract
Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is acceptable. However, these heuristics are not guaranteed to be admissible and can lead to suboptimal plans. We introduce LeanPlan, the first planning system that finds optimal plans with LLM-generated heuristics whose admissibility is machine-checked. Given a domain description and training tasks, an agentic loop uses planner feedback to iteratively improve a reusable domain-specific heuristic, its admissibility proof and the required domain assumptions. LeanPlan implements the heuristic, its proof and an efficient planner with machine-checked grounding and search in Lean 4. We evaluate LeanPlan on ten domains from the International Planning Competition and three new domains, using test tasks with up to 57 times as many objects as the training tasks. With GPT-5.6 Sol in the agentic loop, we successfully generate heuristics and admissibility proofs for all these domains. With the resulting heuristics, LeanPlan usually expands fewer states than the state-of-the-art Scorpion planner and solves more tasks overall.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08246
PDF
-
OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization
2026-10-06 12:17:52Neriah Ben David, Ori Meir, Or OrdentlichAbstract
NVFP4 is an attractive datatype for large language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserving accuracy using NVFP4 requires careful quantization. In this work we develop a novel quantization scheme called Optimized Smoothing and Scaling for NVFP4 (OSFP4). For each linear projection it uses a diagonal smoothing matrix whose entries are optimized to minimize the squared matrix-product quantization error under NVFP4, taking into account the rounding procedure that is used (either round-to-nearest, or GPTQ-style successive interference cancellation). This requires performing joint optimization on the smoothing entries as well as the block scales, which is facilitated by analyzing a multiplicative-dither FP4 quantizer instead of the fixed deterministic one. Experiments show that OSFP4 achieves the highest average accuracy among the evaluated competitors in the corresponding quantization settings, while retaining approximately 94-97\% of vendor NVFP4 prefill throughput on the measured workloads. Our code is available in this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.08231
PDF
-
Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
2026-10-06 11:11:05Zihan Zhou, Xinzhe Hu, Hanxu Yang, Liangjian Wen, Zhao KangAbstract
Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task selection, role assignment, message routing, and context management. As interactions grow, using powerful LLMs for these bounded control decisions introduces substantial token overhead and latency, limiting the scalability of agentic Web services. In this paper, we investigate whether coordination can be decoupled from expensive reasoning without compromising collaborative performance. We propose S1-MAS, a token-efficient multi-agent framework based on System One-guided computational division of labor. S1-MAS assigns bounded coordination decisions to lightweight System One models while reserving open-ended reasoning for capable LLM workers. Specifically, a lightweight controller selects inspection conditions, chooses subsequent tasks, and determines termination, while a compact reader retrieves condition-relevant evidence from authorized sources to support these decisions. Through a decision-evidence loop, selected tasks dynamically determine worker roles and source access, enabling adaptive collaboration without task-specific training. Extensive experiments on seven diverse benchmarks demonstrate that S1-MAS achieves superior accuracy while substantially reducing the inference cost. Across individual comparisons with AgentVerse, DyLAN, and SelfOrg on seven benchmarks, S1-MAS reduces GPT-4o token consumption by 44.9%-97.2% and measured end-to-end latency by 37.8%-93.0%. These results highlight its potential for scalable and cost-effective agentic Web applications.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08155
PDF
-
Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
2026-10-06 10:44:15Sungnyun Kim, Sungwoo Cho, Jihwan Oh, Se-Young YunAbstract
Full-duplex spoken dialogue models listen and speak at the same time, enabling voice agents to have natural, low-latency interactions that turn-based systems cannot offer. However, they are commonly evaluated against single-sided interlocutors: pre-recorded audio that cannot react, or an automated examiner that reacts in real time but only administers a fixed sequence of tests and is never graded. These single-sided frameworks evaluate only half of a two-body problem, where turn-taking, overlap, and interruption are joint products of two coupled speakers. We propose DyaFDB, a framework that evaluates full-duplex models in a dyadic setup: two models converse directly under assigned roles with cooperative or conflicting goals, and both sides are scored offline with an external judge. DyaFDB probes how the two models behave toward each other, such as how they take turns or carry an assigned role under different interests. We instantiate four tasks as 140 scenarios and record 7,560 conversations, covering six self- and cross-play pairings. Throughout the experiments, we observe that how a model behaves continually reshapes its partner. We thus demonstrate that each model must be both the examiner and examinee of the other, and no single fixed interlocutor can play both parts. We will release the scenarios, role prompts, and recording protocols between two full-duplex models, without any pre-recorded audio.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08125
PDF
-
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
2026-10-06 10:24:26Remo Grillo, Lukas Klic, Giovanni ColavizzaAbstract
Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data model. QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations. An offline distiller produces TTQL, a compact description of populated multi-hop patterns, conditional frequencies and path-conditioned literal examples, plus a class-property co-occurrence matrix. Online, TTQL guides the LLM, while deterministic syntax, vocabulary and data-model checks provide diagnostics for iterative refinement. On CK25 (First International Text2SPARQL Challenge), under matched-condition recomputation on a QLever snapshot, QRAKEN achieves strict F1 of 0.643 $\pm$ 0.026 with GPT-4.1 mini and 0.652 $\pm$ 0.012 with GPT-5.4: relative gains of 30% and 32% over the strongest recomputed participant, outperforming systems using the same base model family. Ablations identify TTQL patterns as the dominant driver (+0.31 strict F1 over a shape-only baseline); the refinement loop provides a cheap safety net, rejecting triple patterns unsupported by the co-occurrence matrix. Compared with auto-derived SHACL, TTQL yields 64% higher strict F1, supporting the value of empirical patterns beyond schema exposure. With two local 35B 4-bit open-weight models at zero marginal cost, the same pipeline matches the strongest recomputed participant, and TTQL advantages over shape-only and SHACL baselines persist. Results on a single, relatively small benchmark provide an initial empirical signal; monolithic TTQL injection on very open cross-domain graphs remains the main limitation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08095
PDF
-
Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training
2026-10-06 09:53:25Tobias Hallmen, Elisabeth Andr\'eAbstract
Automatic assessment of communication quality in dyadic counseling conversations is bottlenecked by data: expert-rated corpora are small and expensive to grow. We study cross-domain transfer of expert overall-impression prediction across three German corpora of simulated counseling (two general-practice medical, one school-related parent-teacher; $n=195$ expert-rated sessions, one corpus after scale equating). Training on the other domains beats training in-domain: leave-one-domain-out transfer reaches nested Spearman $\rho = 0.54$ against $\le 0.48$ within the target domain, a paired session-level gap of $+0.15$ that holds at $+0.12$ when the training-set sizes are matched, so it is not simply data volume. The decisive features are session-level construct scores from small open-weight LLMs reading the two-speaker transcript, with the constructs largely derived from the experts' rating instruments: the instrument-derived battery lifts a single judge from $0.32$ to $0.41$ over generic dialogue qualities, judges from three model families ensemble to $0.51$ language-only, and a nonverbal-dyadic block adds $+0.03$ more, not separable from noise at this sample size. We also price the recording setup: one corpus lost its per-speaker audio, 16% of its diarised segments carry the wrong speaker, and repair is worth $+0.07$ there. At practically attainable corpus sizes, the expert's overall impression is carried by what is said, and by other communication programs' data more than by one's own.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08055
PDF
-
Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels
Abstract
Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model either as pixels, at about a thousand visual tokens per image, or as a stored text proxy that often misses the detail the question asks about. We find that the benefit of pixels usually comes from one or two retrieved memories, and that it can be predicted before the answering model runs, without reading any full-resolution image. In PixelTriage, a plug-in placed after retrieval, a small model that does not generate text reads the dialogue, a short note and a thumbnail of each retrieved memory and predicts how much its pixels would add. It is trained on synthetic memory episodes labeled by a frozen 27B model that answers each question with and without each memory's pixels. With a 7B answering model, PixelTriage lies on the accuracy--cost frontier of M$^3$Exam, DMV and MemEye and uses 11--23\% of the visual tokens without a significant loss of accuracy. On DMV it answers 2.9 times faster than opening all images. It outperforms retrieval order and uniform down-sizing at equal budgets and transfers to other memory systems and to a 397B answering model.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07984
PDF
-
SIGMA: Self-Improving Alignment Generalization from a Model Spec
2026-10-06 08:09:56Jingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme, Leon A. Gatys, Joseph Yitan ChengAbstract
LLM agents are increasingly capable of executing complex tasks and of recursively improving themselves on easy-to-verify objectives such as software engineering and mathematics. Since alignment is much harder to verify, this creates a growing risk of capabilities increasing without appropriate safety alignment, especially as capabilities expand to auto-research and cybersecurity. Existing approaches focus on capability self-improvement using verifiable feedback or on alignment training with supervision from stronger models or curated data, creating an external supervision bottleneck for alignment. We ask whether current models can improve their own safety alignment, and propose SIGMA, a data generation and training pipeline enabling alignment self-improvement that generalizes to out-of-distribution settings. Given only a "Model Spec" stating the model's desired behavior, SIGMA leverages a model's reasoning capabilities to strengthen its own safety reasoning. SIGMA first performs spec-guided task synthesis, using the candidate model as a task designer agent to generate diverse alignment dilemma scenarios and convert them into training tasks that stress-test its understanding of the Model Spec. Next, SIGMA conducts self-judged alignment training through supervised fine-tuning and rubric-based reinforcement learning with the model itself as the reward model. Despite training only on single-turn chat data, SIGMA improves safety alignment in multi-turn agentic environments (AgentHarm harmfulness decreases from 22.6 to 14.8; Agentic Misalignment decreases from 79.1 to 3.8), outperforms Deliberative Alignment and Constitutional AI baselines, and retains general capability. Analyses show that a Model Spec balancing harmlessness and helpfulness, test-time reasoning for safety deliberation, and high-quality rubrics from SIGMA's task designer agent are crucial for effective self-improvement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07935
PDF
-
Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations
2026-10-06 07:52:37K. P. Santoso, N. Z. Fadil, F. P. Harsanti, R. V. H. Ginardi, G. N. IyerAbstract
We study sequential content sufficiency by investigating whether a representation retains the ordered target information available in its input. An information-theoretic decomposition separates input ambiguity, representation loss, and readout mismatch. We construct recoverable views where perfect agreement and joint isotropic Gaussianity coexist with zero target information, and establish limits imposed by deterministic canonical anchors. Token log-loss provides a one-sided information-loss bound; a fixed-penalty ridge analysis shows why rank alone cannot determine prediction risk. These results motivate CANOPE, a nonautoregressive framework with ordered latent canvases, canonical-token supervision, and geometric regularization. On 40,000 validation sequences, latent-agreement (PL0) and token-grounded (PL2) have nearly identical pooled ranks but reach 13.5% and 98.8% positional Recall@1, respectively, under strong natural corruption when the correct target length is provided. On 3,930 LJSpeech validation utterances, frozen PL2 with a trained MatchaTTS readout yields 21.54% word error rate (WER) on corrupted text, versus 99.22% for frozen PL0, while end-to-end MatchaTTS reaches 10.93%. These results show that geometric regularity alone does not guarantee recoverable sequential content or effective downstream access in the text settings studied here.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07906
PDF
-
ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning
2026-10-06 07:32:50Miao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu, Chunli LvAbstract
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, resulting in a substantial gap between generic guidelines and executable plans. To bridge this gap, we first propose the personalized fully quantified multiobjective dietary planning problem (MDP). To tackle MDP, we develop a nutrition agent, ShanLiangRen. The system first transforms dietary specifications, nutrient data, user attributes and natural language requirements into an individualized constrained planning instance. It then employs an exact retrieval-augmented generation method to shrink the feasible candidate set from a large scale ingredient and recipe space. Finally, it adopts a refinement guided by Pareto principles, where an LLM iteratively revises candidate plans under deterministic nutrition computation and feedback from constraint verification. The system outputs fully quantified meal plans with explicit ingredients and portion sizes, together with reports on nutrition compliance that show constraint satisfaction and nutrient interval attainment. We have released the system online as a WeChat Program, ShanLiangRen. A demo video is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07886
PDF
