Knowledge
-
Latent space bias directions in LLMs capture confidence, not fairness
2026-10-06 15:42:35Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban, Stuart BurrellAbstract
Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports that steering vectors generalise poorly, with unintended effects on model performance and limited transfer to new datasets. Our work analyses what the debiasing direction used for activation steering actually encodes, in order to shed light on its inconsistent performance. We study the linear debiasing direction obtained by contrasting the activations of anti-biased and biased prompts, and evaluate it as a steering intervention across bias and general knowledge benchmarks. We find that this direction is dominated by model confidence, pointing from regions of high to low-probability tokens in activation space rather than encoding a meaningful representation of model bias. Steering along it does reduce measured bias, but this is a consequence of reducing model confidence: on QA benchmarks we find that this steering drives the model to abstain from answering, with a side effect of improving fairness metrics. Our experiments show that model confidence is the dominant separating factor between biased and anti-biased prompts in hidden space, indicating that isolating a linear representation of bias which is disentangled from model confidence is difficult and steering-based debiasing results should be interpreted with care. In short, steering appears to reduce bias, not by correcting the model's underlying preferences, but by making it less confident, even on tasks unrelated to bias.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08559
PDF
-
Systemization of Knowledge : Human-Centered AI Safety for Youth
Abstract
While HCI increasingly examines AI-safety for youth, the literature lacks a comprehensive view of what risks have been identified, how they are addressed, and whether proposed protections work in-practice. We systematically reviewed 100 empirical HCI studies involving children and youth interacting with or exposed to AI across schools, homes, care settings, and public services. Using the YAIR taxonomy for risks and the MIT Mitigation Taxonomy for countermeasures, we map which risks have been identified, whether each risk is addressed by countermeasure(s), and whether each countermeasure for that risk is implemented and even evaluated. The risk-countermeasure mapping shows that most risks are matched only with proposed/ideated countermeasures; few countermeasures have been implemented, and fewer still evaluated; and existing evaluations often measure technical performance rather than protection from harm. We identify where coverage is absent, where safeguards remain untested, and propose concrete directions for HCI research to strengthen youth AI-safety.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08554
PDF
-
From Shared Demand Patterns to Local Uncertainty: Probabilistic Load Forecasting by Mixing Compact Adaptations
2026-10-06 15:27:43Haoran Li, Zhe Cheng, Yang WengAbstract
Probabilistic load forecasting has been widely studied for power-system operation and planning, but customer- and transformer-level forecasting introduces a distinct scalability challenge. At these levels, load uncertainty is strongly affected by customer behavior, weather, and mixed load composition, making it difficult for a single shared model to capture heterogeneous patterns. Using separate probabilistic models can improve local accuracy, but becomes costly to train, store, update, and validate at scale. To address this challenge, we develop a scalable customer-aware forecasting framework that learns common demand behavior through a shared model while adapting only a compact subset of parameters. Rather than using an independent model for each load or assigning each load to a specialized model, the proposed design learns a small bank of low-dimensional adaptation components and allows each load to combine them according to its forecasting characteristics. This preserves shared knowledge across customers while providing sufficient flexibility for heterogeneous and mixed load compositions. Experiments on 590 load profiles from the SMART-DS dataset show consistent improvements in deterministic accuracy and probabilistic quality over statistical, neural-network, Transformer-based, and pretrained time-series baselines, while retaining low storage and inference costs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08538
PDF
-
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
2026-10-06 14:38:15Lasse B. Strand, Robert Jakob, Kevin O'Sullivan, Markus KreftAbstract
Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing optimizers, from greedy search to Bayesian optimization, reduce each trial to an aggregate score and search without modeling why a configuration performed as it did, even though the retrieved chunks already provide evidence about whether each failure occurred during retrieval or after it. We introduce Agentic AutoRAG, an LLM-agent optimizer for multi-objective RAG hyperparameter optimization with retrieval-versus-generation failure attribution. It proposes configurations scored on a frozen exam from the corpus: after each trial a Diagnoser attributes each failed question to retrieval or generation, and a Proposer, grounded in a knowledge base of model rankings and pricing, selects the next configuration, weighing accuracy against cost to trace a Pareto frontier. On three multi-hop QA benchmarks it reaches higher LLM-judge accuracy than every baseline we compare, and within its first 10 trials it matches or beats the statistical baselines' full 30-trial judge accuracy. In its cost-aware mode on a real-world healthcare corpus it reaches a median exam accuracy of 77%, above the strongest baseline's 71.5%, at about 58% of that baseline's cost per query, and it matches that 71.5% at about 22% of the cost.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08452
PDF
-
Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
2026-10-06 14:07:43Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua HuAbstract
Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge source for reliable reasoning. However, existing LLM-guided graph reasoning methods typically rely on hop-wise greedy or beam-style pruning during evidence retrieval. Such local decision processes are inherently myopic: evidence that appears weak near the source may become crucial only after deeper graph context is explored, causing answer-critical branches to be discarded prematurely and making the reasoning chain difficult to recover. To address this limitation, we propose Foresight-over-Graph (FoG), a foresight-aware evidence retrieval framework for knowledge base question answering (KBQA). FoG iteratively constructs a question-relevant evidence subgraph and uses far-to-near feedback to guide path exploration, and maintains a compact memory subgraph to support continued exploration. Extensive experiments on widely used KBQA benchmarks demonstrate that FoG achieves state-of-the-art performance, with a particularly large improvement of 16.58% in Hit on CWQ, while also reducing LLM calls and token usage. Our code is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2610.08388
PDF
-
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
2026-10-06 13:25:55Xilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang, Xiaowei Hu, Jinpeng Li, Pheng-Ann HengAbstract
Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric knowledge and costly expert supervision. Self-evolving agents offer a promising alternative by enabling models to improve through iterative task generation and problem-solving. However, most existing self-evolving methods are designed for easily verifiable domains such as mathematics and coding, where solutions can be checked by exact answers or executable programs. Medical reasoning is fundamentally different: it is open-ended, knowledge-intensive, and often only partially verifiable. We present MedZERO, a self-evolving framework for open-ended medical reasoning. MedZERO couples an Examiner that generates frontier medical question-option pairs with a Reasoner that solves them through evidence-grounded multi-turn reasoning with external knowledge tools. To support reliable, continual improvement, MedZERO adopts controlled knowledge accumulation, which maintains temporary exploratory knowledge and curated persistent knowledge in reasoning. We evaluate MedZERO on five public medical reasoning benchmarks using 4B- and 8B-scale base models under open-ended evaluation. Across all settings, MedZERO consistently outperforms the underlying base models and prior self-evolving baselines, achieving up to 13.7 average accuracy-point gains over the next-best self-evolving baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08327
PDF
-
Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance
2026-10-06 13:18:10Khac Duc Giang Nguyen, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor AlsahagAbstract
Counter-UAV systems based on thermal infrared detection must stay accurate as operational datasets evolve, yet sequential fine-tuning causes catastrophic forgetting of prior tasks, a problem that remains insufficiently characterized in this domain. This continual-learning study measures the stability-plasticity trade-off in YOLOMG, a YOLOv5-based detector run as a single thermal-infrared stream with the motion channel disabled, trained sequentially across three anti-UAV benchmarks of rising scale difficulty: Anti-UAV-RGBT, Anti-UAV410, and CST Anti-UAV. Naive fine-tuning on CST yields a Forgetting Measure of -0.605 against the Stage 1 ceiling, corresponding to a 90% capability loss, with -0.572 occurring in Stage 3 alone. In contrast, knowledge distillation from a frozen teacher is associated with FM = -0.033 +/- 0.004 across three seeds, corresponding to 95% retention. Because no Stage 2 no-KD control is included, this result establishes retention under KD training rather than a causal KD effect. Per-stratum analysis shows large-target detection collapsing to near zero within the first epoch, despite an inter-stage cosine similarity of 0.987 over the gradient-updated weights, pointing to scale-conditioned gradient imbalance, rather than weight drift, as a candidate mechanism. Scale-Stratified Herding (SSH), a 300-exemplar buffer balanced across four UAV size strata, roughly halves the forgetting (FM = -0.605 to -0.311) and keeps large-target detection non-zero. An ablation attributes the gain primarily to scale stratification rather than herding: random-stratified replay performs at least as well (FM = -0.221 versus -0.311 for SSH). These replay results are single-seed and should therefore be treated as preliminary.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08315
PDF
-
CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
2026-10-06 13:17:25Maoqi Liu, Quan Fang, Yufei HeAbstract
Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, recent advances implement low-rank adaptation with orthogonal projections (e.g., O-LoRA) to isolate task parameters. However, we reveal that such strict geometric constraints trigger an "Orthogonality Dilemma": rigid parameter isolation impedes the transfer and accumulation of shared representations across semantically related tasks. In this work, we propose a new replay-free method, called Consolidation and Decoupling LoRA (CoDe-LoRA), for CL of LLMs. CoDe-LoRA disentangles the learning process into Consolidating Universal Knowledge and Decoupling Task-Specific Knowledge. To achieve this, CoDe-LoRA leverages an adaptive null space projection mechanism and semantic routing to balance knowledge accumulation with task-specific adaptation. Experimental results across four backbones and three CL benchmarks show that CoDe-LoRA achieves the best average accuracy. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08312
PDF
-
zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
2026-10-06 12:35:49Junkai Liang, Zhanpeng Guo, Pengfei Wu, Qingni Shen, Jiaheng Zhang, Zhonghai Wu, Haiyang Xue, Shengfang ZhaiAbstract
Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory. zkLLMPoT includes 2 phases: 1) The trainer fixes the architecture and the model weights are committed. Then the auditor selects challenge sequences, preventing the trainer from modifying the checkpoint in response to the audit data. 2) Then the trainer proves the objective value attained by the committed model on those sequences. This formulation makes the certification cost independent of the number of training iterations, without revealing model weights or requiring access to private training data. We build on sumcheck- and lookup-based arguments to certify Transformer computations, while supporting next-token loss and task-specific audit objectives. Across four model families, operator-level benchmarks yield proving times of 41-59 seconds for 1.1-1.5B-parameter models and 131 seconds at 13B for the covered operators, with verification below half a second at a sequence length of 512.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08258
PDF
-
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
2026-10-06 12:08:45Yibo Li, Jinhang Qiu, Zhi Zheng, Qianyun Guo, Jiaying Wu, Shuo Ji, Bryan HooiAbstract
Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effectively agents acquire and use new knowledge. Existing benchmarks have sought to evaluate this ability, but they primarily evaluate tasks whose rules are provided in the instructions or already familiar to pretrained models, making it difficult to distinguish learning from interactions from reasoning with existing knowledge. To address this, we introduce Learn2Play Bench, a benchmark of newly designed text-based games, whose rules are novel or counterintuitive, requiring agents to acquire knowledge through interaction rather than rely solely on pretrained knowledge. These games provide reproducible feedback and automatic scoring, enabling controlled evaluation of learning across repeated attempts. We also vary game instances to test whether agents can apply what they have learned to new situations. Therefore, we evaluate how backbone models, self-evolving methods, and agent harnesses affect agents' learning ability, revealing three findings: (1) Experience retention: Retaining complete records of actions and feedback can support more effective learning than summarizing these experiences into rules or strategies. (2) Human agent gap: Top-performing human players achieve higher peak scores than the evaluated agents. Human explore more varied strategies, and repeat actions less. (3) Harness matters: With the backbone fixed, changing the harness can improve performance while reducing estimated inference cost. Together, these findings provide insights into how LLM agents learn from experience and suggest directions for future work to improve their learning ability. Project website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.08215
PDF
-
Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek
2026-10-06 11:58:55Nikolaos D. Tantaroudas, Ilias Karachalios, Andrew J. McCrackenAbstract
Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-augmented generation (RAG). We compare the two on KyGround, a benchmark of 198 questions drawn from the published records of a Greek--English agricultural platform on Kythera, Greece, with answers verified automatically against the records and each question posed in up to nine forms, including Greek without accents, in capitals and in three Latin-script (Greeklish) schemes. With Claude Haiku 4.5 as router and answer model, a reconstruction of the platform's tool agent answered 71.6\% of canonical Greek questions correctly and vector RAG 95.3\% (difference $-23.6$ percentage points, 95\% CI $-33.1$ to $-15.1$). Letting the router write the vector query changed nothing, and placing the whole knowledge base of about 26,000 tokens in the prompt reached 99.3\%. The tool agent's losses arose in retrieval. Its literal searches returned nothing when the router's arguments did not occur verbatim in a record, for example when it transliterated Greek into Latin script or combined words that occur in a record but not as one phrase, and the agent then abstained. Unaccented and capitalised questions cost the tool agent about 20 points and vector RAG at most 2; accent-insensitive search removed this loss, and matching stemmed tokens raised the tool agent to 83.8\% on canonical Greek. Greeklish cost both designs about 21 to 32 points. Tool interfaces for community knowledge bases need search that tolerates how users type.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08205
PDF
-
Which alloy composition,what process parameters? Inferring the recipe from optimized metallic microstructure and texture
2026-10-06 11:22:44Mahish K. Guru, Jan Bohlen, Louam Lemjid, Marius Tacke, Roland Aydin, Noomane Ben KhalifaAbstract
The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their crystals. That structure is in turn set by a recipe, the alloy composition together with the processing parameters. Alloy development runs this chain forwards, tuning the structure until a target property is met. Running it backwards, from an optimized structure to the recipe that would produce it, still relies on expert knowledge. We ask whether this backwards step can be learned. On an in-house dataset of 107 magnesium alloy extrusion conditions across 14 alloys, each with optical micrographs and an X-ray texture measurement, we compare three descriptors of microstructure and texture: conventional grain and texture statistics, a vision embedding from a pretrained image encoder, and a graph neural network on the grain network. Each is paired with prediction heads for two tasks: the alloy composition given the process (Task A), and the process parameters given the composition (Task B). Under 5-fold cross-validation, the conventional descriptors identify the correct alloy for 65% of held-out conditions, against 17% for always guessing the most common alloy, while the learned embeddings stay below 30%. The process parameters are recoverable but noisier: compared with using the composition alone, the microstructure roughly halves the temperature error. Because only a few alloys were cast and only a few press settings were used, both answers are discrete, and heads that pick from these known options, while respecting their order, worked better than heads that predict a free value.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08165
PDF
-
Context-Conditioned Hamilton-Jacobi Reachability for Adaptive Safety Filtering
2026-10-06 10:36:41Ali Fuat Sahin, Yunus Yazoglu, John Talbot, Zeyuan Feng, James Dallas, Somil BansalAbstract
Hamilton-Jacobi reachability constructs safety certificates for specified dynamics and safety constraints, tying each certificate to the deployment context for which it is synthesized. We ask whether a single certificate can instead represent a family of context-dependent safety problems and be queried across deployment conditions without re-synthesis. We learn a backward reachable tube for an eight-state vehicle model conditioned on local boundary geometry, friction coefficient, and adversarial disturbance scale. Geometry enters through an ego-frame boundary observation that defines the local containment constraint, while friction and disturbance scale enter as explicit operating-condition variables. This allows the same value function to be queried across friction coefficients from 0.4 to 2.0 and on geometries absent from synthesis. On 11 held-out evaluation geometries, the certificate maintains containment across the full tested friction range, including simultaneous geometry and grip shifts, while remaining within 1.2 percentage points in intervention rate and 0.09 m/s in speed of certificates re-synthesized with knowledge of the test geometry. We then deploy the certificate as a sampled discrete-time control barrier function filter on a full-scale vehicle near the handling limit. Lateral containment holds in every hardware session under both adversarial driving and autonomous racing, with 99th-percentile acceleration magnitude reaching 0.99 g. Across three certificates evaluated under a fixed autonomous racing controller, lap time varies by only 3.1%, demonstrating that a context-conditioned reachability certificate can transfer to deployment geometries absent from synthesis with modest performance cost.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08115
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
-
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
2026-10-06 10:06:47Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi, Zhuofeng Li, Siming Zhang, Jiaxin Zhang, Jixuan Chen, Fang Wu, Pan Lu, Silvio Savarese, Julian McAuley, Chien-Sheng WuAbstract
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative objectives, however, this signal vanishes when all rollouts receive the same reward, even though their trajectories may reveal useful information about what the task requires and how the agent fails. We ask a complementary question: can hindsight teach an agent what it could have anticipated before acting? We introduce prospective learning, which uses post-hoc experience to supervise foresight predictions from the pre-interaction view, and instantiate it with Self-Retrospection Distillation (SRD). Intuitively, a completed trajectory reveals knowledge that would have been useful and pitfalls that should be avoided; SRD distills this privileged hindsight into trajectory-blind foresight of the same policy. Foresight serves only as a training target and need not be explicitly generated at inference time. Across 10 tool-integrated reasoning and long-horizon agentic tasks, SRD complements RLVR and self-distillation baselines with gains of up to $24.2$ pp. Its advantage is especially pronounced when reward contrast is scarce: when $37$--$98\%$ of rollout groups are reward-uniform across model scales, yet SRD can still exploit learning signal from sampled trajectories. In the 2B setting, where $98\%$ of groups are all-failure, the RLVR training ends up at $0.0\%$ success, while adding SRD reaches $60.6\%$ under the same rollout budget. Our results suggest that post-hoc agent experience is useful not only for evaluating or improving behavior, but also for shaping predictive representations before available interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08077
PDF
-
SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning
2026-10-06 10:06:25Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike, Abdelrahman Madkour, Varun Prashant Gangal, Monty Bichouna, Martyna Markiewicz, Shivani Jain, Duncan Curtis, Rebecca Qian, Anand KannappanAbstract
Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertinent question of whether LLM agents can go beyond what humans have already solved. The ability to develop sophisticated strategies to tackle consequential problems becomes paramount as well-trodden, human-developed solutions become insufficient for problems for which we lack context or enough training data. We study agents' capability of such strategy formation through the communal practice of video game speedrunning. In speedrunning, practitioners compete to find the fastest way to complete a video game under certain conditions, and in so doing uncovering interesting unorthodox play styles that require a thorough understanding and mastery of the underlying game mechanics. We introduce SPEEDRUNBENCH, a benchmark that evaluates frontier LLM agents across 9 different games. To perform well in this benchmark, agents must repeatedly improve their strategy, reflect on their performance, exploit their gained knowledge, and reason across a long-horizon of actions to improve on an increasingly difficult problem: being faster than themselves and everyone else. Our experiments show that while frontier agents approach human world records in simple platformer games, they remain behind human performance on longer, more complex games under practical budgets. These results suggest that SPEEDRUNBENCH is a useful testbed for studying agents' strategy formation capabilities as well as being a saturation-resistant evaluation measure, as there is almost always a faster completion time waiting to be discovered.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08076
PDF
-
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
2026-10-06 09:46:32Antoine Edy, Max Conti, Victor Xing, Marc-Antoine Allard, Nawfal Benhamdane, Gautier ViaudAbstract
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the environment. We present DAEDALUS, a method for bootstrapping reusable agent memory from self-generated practice without existing tasks or oracle verifiers. DAEDALUS pairs two agents: an explorer that interacts with the environment to generate challenging yet solvable tasks, and a solver that attempts them. A heuristic is derived from each solver failure and accepted only after the solver repeatedly succeeds with that heuristic in context. These outcomes also provide feedback for the explorer to refine the difficulty of future tasks. Accepted heuristics are then consolidated into a memory bank for test-time use. Across AppWorld, $\tau^2$-bench, and AutomationBench, DAEDALUS improves mean success rates by up to 15.9 points and pass^5 by up to 2.2x over a no-memory baseline, and is competitive with methods using training tasks, at a lower inference cost than most. We show that performance gains already emerge with a small exploration budget, and that its heuristics also benefit agents from other model families. Our ablations further reveal that solver traces provide the key information needed to derive effective heuristics, while factorizing early discoveries makes exploration more cost-efficient. Beyond memory construction, we find that the tasks generated by DAEDALUS can serve as a proxy for benchmark tasks when ranking models by performance. Code and artifacts: this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08048
PDF
-
Are Language Models Script-Aware?
2026-10-06 09:31:04David Kletz, Sandra Mitrovi\'c, Ljiljana Dolami\'c, Fabio RinaldiAbstract
Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research has focused on language selection, the dimension of script knowledge remains understudied: before any linguistic understanding can occur, users must recognize the graphic symbols in a model's response. We investigate whether Small and Large Language Models (SLMs and LLMs) possess script knowledge by testing them on multi-scriptic languages. Through two complementary experiments, we evaluate whether models (1) adapt their output script to match the input, and (2) follow explicit instructions to generate text in a specified script. The models we tested demonstrate substantial script knowledge: they all achieve a near-perfect Latin script fidelity (more than 98%) and follow script instructions with high frequency. Nevertheless, we notice differences between LLMs and SLMs, with higher scores for LLMs including for non-standard script combinations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08037
PDF
-
Same Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback Analysis
2026-10-06 09:29:25Viraj Bagal, Raviraja Ganta, Prabhath ChellingiAbstract
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer appears plausible. We introduce a repeat-run evaluation framework that aligns semantically equivalent categories and focuses on two operating metrics: theme churn, the normalized change in the returned category set, and volume disagreement, the change in counts for categories that persist. We evaluate three recurring customer-feedback tasks across eight frontier models, corpus sizes from 100 to 5,000 records, multiple prompts, and three execution designs: raw generation, taxonomy-free hierarchical decomposition, and a taxonomy-grounded agent (TGA) using persistent themes, subthemes, and record-level predictions. With Claude Opus 4.8 and the 1,000-record corpus fixed, TGA reduces theme churn by 86--88% relative to both raw generation and hierarchical decomposition, while matched-theme volumes have zero disagreement. The taxonomy-grounded agent is more stable than every raw model in the screen, remains more stable at each corpus size, and keeps this advantage when theme matching is made stricter or looser. Although evaluated on customer feedback, the framework targets repeated synthesis of unstructured corpora more broadly, including financial reports, legal documents, incident records, and scientific literature. Overall, these results show that taxonomy grounding produces more consistent and repeatable outputs for recurring knowledge work.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08036
PDF
-
Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction
2026-10-06 08:28:52JunGyu Lee, Inhwan Bae, Hae-Gon JeonAbstract
Language-based trajectory predictors represent coordinates as discrete tokens and learn auxiliary tasks such as destination and group reasoning. This formulation enables the model to capture behavioral intent and social context beyond coordinate dynamics alone. However, token-level objectives provide only indirect guidance for continuous coordinate-space dynamics. To address this limitation, we introduce MoRE (Mixture of Reward Experts), a refinement framework that transfers numerical forecasting priors into a pretrained language-based predictor through reinforcement learning. Five frozen numerical predictors provide complementary coordinate-level knowledge of motion and interactions. Their predictions are converted into expert rewards and combined through an uncertainty-weighted consensus that penalizes disagreement. A ground-truth reward anchors the prediction to the target trajectory. To focus refinement on difficult cases, MoRE refines the policy using the top 1% of training samples ranked by predictive entropy. Expert predictions are computed once and cached before PPO training, so the experts are not run during policy updates or inference. In this way, MoRE combines the contextual modeling of the language-based predictor with coordinate-level feedback from numerical experts. On ETH-UCY, MoRE reduces ADE from 0.22 to 0.20 m and FDE from 0.32 to 0.29 m. Relative to the base policy, ADE decreases by 17.9% on SDD and 12.7% on NBA. On ETH-UCY, MoRE also reduces collision rates and better matches ground-truth pedestrian spacing, without increasing measured inference memory or latency. The project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07954
PDF
