Large language models (LLMs) are increasingly used as coding assistants, but the programs they generate often fail. Such failures can be addressed by debugging the existing implementation or regenerating a new solution from the problem specification, with existing repair workflows typically defaulting to debugging. We find that the effectiveness of debugging and regeneration depends strongly on initial program quality, suggesting that no single repair strategy is universally optimal. Motivated by this observation, we present PATSSEL (Program-Adaptive Test-guided Repair Strategy Selection), a test-guided repair selection framework that dynamically chooses between debugging and regeneration. Rather than committing to a single repair strategy, PATSSEL generates debugged and regenerated candidates for each buggy program, evaluates them using generated verifier tests, and selects the stronger candidate, leveraging the complementary strengths of debugging and regeneration. Experiments on LeetCodeDataset, LiveCodeBench, and HE+Fix show that PATSSEL achieves average absolute improvements of 2.7% with Qwen3-8B and 3.2% with Llama3-8B over the best single-strategy baselines under the same inference compute budget and routing using gold unit tests. The gains persist across repair models, routing models, and stronger debugger models. Further analysis shows that PATSSEL benefits from the complementary strengths of debugging and regeneration, highlighting the importance of adaptive strategy selection for reliable LLM-based code repair.

Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HIVIG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories to abstract past interactions into a compact record and to evaluate actions with visual grounding. At test time, HIVIG integrates the critic into the policy decision loop to provide macro-action history, which summarizes the policy’s completed achievements, and visually grounded critique, which verifies raw execution coordinates against the current screenshot to intercept errors before execution. Across web, mobile, and desktop benchmarks, HIVIG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash, and demonstrates strong cross-platform generalization. Ablations show that macro-action history mitigates short-sighted planning and visually grounded critique reduces execution errors, with both components being critical for test-time scaling in long-horizon GUI tasks.

Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at their answers. Moreover, optimizing for faithfulness and interpretability in reasoning often degrades task performance. To address this tradeoff and improve CoT faithfulness, we propose Reasoning Execution by Multiple Listeners (REMuL), a multi-party reinforcement learning approach. REMuL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful. A speaker model generates a reasoning trace, which is truncated and passed to a pool of listener models who “execute” the trace, continuing the trace to an answer. Speakers are rewarded for producing reasoning that is clear to listeners, with additional correctness regularization via masked supervised finetuning to counter the tradeoff between faithfulness and performance. On multiple reasoning benchmarks (BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO), REMuL consistently and substantially improves three measures of faithfulness – hint attribution, early answering area over the curve (AOC), and mistake injection AOC – while also improving accuracy. Our analysis finds that these gains are robust across training domains and are associated with shorter and more direct CoTs.

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior work has largely combined these data types without examining their distinct effects. In this paper, we investigate how training LLMs with or without context affects model behavior and downstream performance. First, in the text domain, we show that LLMs trained with context attend more strongly to the provided knowledge, achieving better grounding. We also observe that context-augmented training shifts how LLMs use knowledge: models store and leverage less on parametric knowledge and instead depend more on the provided context. Second, we observe that using LLM trained with context-augmented data as the backbone for vision-language models reduces hallucination and improves grounding in the visual domain. Finally, we explore practical strategies for real-world deployments where context availability varies. We show that maintaining separate context-augmented and context-free models and routing inputs between them yields more robust overall performance than training a single mixed model, as it better preserves their complementary strengths.

LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online Adaptation to Continual Knowledge Streams(OAKS) to evaluate this capability, establishing a benchmark for online adaptation over streaming, continually updating knowledge. Specifically, the benchmark is structured as a sequence of fine-grained context chunks where facts change dynamically across time intervals. OAKS comprises two datasets: OAKS-BABI and OAKS-Novel, where individual facts evolve multiple times across context chunks. These datasets include dense annotations to measure whether models track changes accurately. Evaluating 14 models with varied inference approaches, we observe significant limitations in current methodologies. Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS, demonstrating delays in state-tracking and susceptibility to distraction within streaming environments. We will open-source the code and datasets.

In a real-world corpus, knowledge frequently recurs across documents but often contains inconsistencies due to ambiguous naming, outdated information, or errors, leading to complex interrelationships between contexts. Previous research has shown that language models struggle with these complexities, typically focusing on single factors in isolation. We classify these relationships into four types: distracting, ambiguous, counterfactual, and duplicated. Our analysis reveals that no single approach effectively addresses all these interrelationships simultaneously. Therefore, we introduce Context Organizer (COrg), a framework that organizes multiple contexts into independently processed groups. This design allows the model to efficiently find all relevant answers while ensuring disambiguation. COrg consists of three key components: a graph constructor, a reranker, and an aggregator. Our results demonstrate that COrg balances performance and efficiency effectively, outperforming existing grouping methods and achieving comparable results to more computationally intensive, single-context approaches.

Hybrid models that combine state space models (SSMs) with attention mechanisms have demonstrated strong performance by leveraging the efficiency of SSMs and the high recall ability of attention. However, the underlying reasons for these benefits remain insufficiently understood. In this work, we investigate hybrid architectures through the lens of memory utilization and overall performance, and propose a complementary method to further enhance their effectiveness. We focus in particular on the distinction between sequential and parallel integration of SSM and attention layers. Our analysis reveals that sequential hybrids perform better on shorter contexts, whereas parallel hybrids are more effective for longer contexts. Among various configurations, parallel hybrids using a cross-attention to combine SSM and attention outputs perform best. We also introduce a data-centric approach to further improve model performance: continual training on datasets with paraphrases. This method strikes the best balance across various other datasets, enhancing memory recall while preserving other capabilities. It generalizes well across different base models, including pure SSMs, and outperforms architectural modifications aimed at enhancing recall.

Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora). However, in realistic scenarios, this is rarely the case and the documents to be retrieved are constantly updated and added. In this paper, we focus on Generative Retrievals (GR), which apply autoregressive language models to IR problems, and explore their adaptability and robustness in dynamic scenarios. We also conduct an extensive evaluation of computational and memory efficiency, crucial factors for real-world deployment of IR systems handling vast and ever-changing document collections. Our results on the StreamingQA benchmark demonstrate that GR is more adaptable to evolving knowledge (4–11%), robust in learning knowledge with temporal information, and efficient in terms of inference FLOPs (x2), indexing time (x6), and storage footprint (x4) compared to Dual Encoders (DE), which are commonly used in retrieval systems. Our paper highlights the potential of GR for future use in practical IR systems within dynamic environments.