MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark

Understanding real-world videos such as movies requires integrating visual and dialogue cues to answer complex questions. Yet existing VideoQA benchmarks struggle to capture this multimodal reasoning and are largely not open-ended, given the difficulty of evaluating free-form answers. In this paper, we introduce a novel open-ended multi-modal VideoQA benchmark, MovieRecapsQA created using movie recap videos--a distinctive type of YouTube content that summarizes a film by presenting its key events through synchronized visual (recap video) and textual (recap summary) modalities. Using the recap summary, we generate $\approx 8.2$ K question-answer (QA) pairs (aligned with movie-subtitles) and provide the necessary "facts" needed to verify an answer in a reference-free manner. To our knowledge, this is the first open-ended VideoQA benchmark that supplies explicit textual context of the input (video and/or text); which we use for evaluation. Our benchmark provides videos of multiple lengths (i.e., recap-segments, movie-segments) and categorizations of questions (by modality and type) to enable fine-grained analysis. We evaluate the performance of seven state-of-the-art MLLMs using our benchmark and observe that: 1) visual-only questions remain the most challenging; 2) models default to textual inputs whenever available; 3) extracting factually accurate information from video content is still difficult for all models; and 4) proprietary and open-source models perform comparably on video-dependent questions.

Better LLM Reasoning via Dual-Play

Large Language Models (LLMs) have achieved remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR), yet still rely heavily on external supervision (e.g., curated labels). Adversarial learning, particularly through self-play, offers a promising alternative that enables models to iteratively learn from themselves - thus reducing reliance on external supervision. Dual-play extends adversarial learning by assigning specialized roles to two models and training them against each other, fostering sustained competition and mutual evolution. Despite its promise, adapting dual-play training to LLMs remains limited, largely due to their susceptibility to reward hacking and training instability. In this paper, we introduce PasoDoble, a novel LLM dual-play framework. PasoDoble adversarially trains two models initialized from the same base model: a Proposer, which generates challenging questions with ground-truth answers, and a Solver, which attempts to solve them. We enrich the Proposer with knowledge from a pre-training dataset to ensure the questions' quality and diversity. To avoid reward hacking, the Proposer is rewarded for producing only valid questions that push the Solver's limit, while the Solver is rewarded for solving them correctly, and both are updated jointly. To further enhance training stability, we introduce an optional offline paradigm that decouples Proposer and Solver updates, alternately updating each for several steps while holding the other fixed. Notably, PasoDoble operates without supervision during training. Experimental results show that PasoDoble can improve the reasoning performance of LLMs. Our project page is available at https://hcy123902.github.io/PasoDoble.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even for simple queries -- leading to increased inference costs and latency. While recent approaches attempt to control verbosity by adding length penalties to the reward function, these methods rely on fixed penalty terms that are hard to tune and cannot adapt as the model's reasoning capability evolves, limiting their effectiveness. In this work, we propose an adaptive reward-shaping method that enables LLMs to "think fast and right" -- producing concise outputs without sacrificing correctness. Our method dynamically adjusts the reward trade-off between accuracy and response length based on model performance: when accuracy is high, the length penalty increases to encourage faster length reduction; when accuracy drops, the penalty is relaxed to preserve correctness. This adaptive reward accelerates early-stage length reduction while avoiding over-compression in later stages. Experiments across multiple datasets show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy, offering a new direction for cost-efficient adaptive reasoning in large-scale language models.

HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization

While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in verbose outputs and increases inference cost. Prior approaches for efficient test-time scaling, typically using universal budget constraints or query-level length optimization, do not leverage historical information from previous encounters with the same problem during training. We hypothesize that this limits their ability to progressively make solutions more concise over time. To address this, we present History-Aware Policy Optimization (HAPO), which keeps track of a history state (e.g., the minimum length over previously generated correct responses) for each problem. HAPO employs a novel length reward function based on this history state to incentivize the discovery of correct solutions that are more concise than those previously found. Crucially, this reward structure avoids overly penalizing shorter incorrect responses with the goal of facilitating exploration towards more efficient solutions. By combining this length reward with a correctness reward, HAPO jointly optimizes for correctness and efficiency. We use HAPO to train DeepSeek-R1-Distill-Qwen-1.5B, DeepScaleR-1.5B-Preview, and Qwen-2.5-1.5B-Instruct, and evaluate HAPO on several math benchmarks that span various difficulty levels. Experiment results demonstrate that HAPO effectively induces LLMs' concise reasoning abilities, producing length reductions of 33-59% with accuracy drops of only 2-5%.

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy rather than improve it. In this paper, we conduct a systematic empirical study of the relationship between reasoning length and answer correctness. We find that LLMs tend to overthink simple problems, generating unnecessarily long outputs, and underthink harder ones, failing to extend their reasoning when it is most needed. This indicates that models might misjudge problem difficulty and fail to calibrate their response length appropriately. Furthermore, we investigate the effects of length reduction with a preference optimization algorithm when simply preferring the shorter responses regardless of answer correctness. Experiments show that the generation length can be significantly reduced while maintaining acceptable accuracy. Our findings highlight generation length as a meaningful signal for reasoning behavior and motivate further exploration into LLMs' self-awareness in reasoning length adaptation.

Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning

While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and reasoning errors, especially in multi-hop tasks that require integration of multiple information sources. Current methods address these issues through retrieval-based techniques (grounding reasoning in external evidence), reasoning-based approaches (enhancing coherence via improved prompting), or hybrid strategies combining both elements. One prominent hybrid method, ReAct, has outperformed purely retrieval-based or reasoning-based approaches; however, it lacks internal verification of intermediate reasoning steps, allowing potential errors to propagate through complex reasoning tasks. In this paper, we introduce Reasoning Court (RC), a novel framework that extends iterative reasoning-and-retrieval methods, such as ReAct, with a dedicated LLM judge. Unlike ReAct, RC employs this judge to independently evaluate multiple candidate answers and their associated reasoning generated by separate LLM agents. The judge is asked to select the answer that it considers the most factually grounded and logically coherent based on the presented reasoning and evidence, or synthesizes a new answer using available evidence and its pre-trained knowledge if all candidates are inadequate, flawed, or invalid. Evaluations on multi-hop benchmarks (HotpotQA, MuSiQue) and fact-verification (FEVER) demonstrate that RC consistently outperforms state-of-the-art few-shot prompting methods without task-specific fine-tuning.

Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model (LLM) hallucinations by incorporating external knowledge retrieval. However, existing RAG frameworks often apply retrieval indiscriminately,leading to inefficiencies-over-retrieving when unnecessary or failing to retrieve iteratively when required for complex reasoning. Recent adaptive retrieval strategies, though adaptively navigates these retrieval strategies, predict only based on query complexity and lacks user-driven flexibility, making them infeasible for diverse user application needs. In this paper, we introduce a novel user-controllable RAG framework that enables dynamic adjustment of the accuracy-cost trade-off. Our approach leverages two classifiers: one trained to prioritize accuracy and another to prioritize retrieval efficiency. Via an interpretable control parameter $\alpha$, users can seamlessly navigate between minimal-cost retrieval and high-accuracy retrieval based on their specific requirements. We empirically demonstrate that our approach effectively balances accuracy, retrieval cost, and user controllability, making it a practical and adaptable solution for real-world applications.

Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning attacks, where malicious passages injected into retrieval databases can mislead the model into generating factually incorrect outputs. In this paper, we investigate both the retrieval and the generation components of RAG systems to understand how to enhance their robustness against such attacks. From the retrieval perspective, we analyze why and how the adversarial contexts are retrieved and assess how the quality of the retrieved passages impacts downstream generation. From a generation perspective, we evaluate whether LLMs' advanced critical thinking and internal knowledge capabilities can be leveraged to mitigate the impact of adversarial contexts, i.e., using skeptical prompting as a self-defense mechanism. Our experiments and findings provide actionable insights into designing safer and more resilient retrieval-augmented frameworks, paving the way for their reliable deployment in real-world applications.

Commit0: Library Generation from Scratch

With the goal of benchmarking generative systems beyond expert software development ability, we introduce Commit0, a benchmark that challenges AI agents to write libraries from scratch. Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests, with the goal of producing an implementation of this API accordingly. The implementation is validated through running these unit tests. As a benchmark, Commit0 is designed to move beyond static one-shot code generation towards agents that must process long-form natural language specifications, adapt to multi-stage feedback, and generate code with complex dependencies. Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate. Our experiments demonstrate that while current agents can pass some unit tests, none can yet fully reproduce full libraries. Results also show that interactive feedback is quite useful for models to generate code that passes more unit tests, validating the benchmarks that facilitate its use.

Are Triggers Needed for Document-Level Event Extraction?

Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span -- a word or phrase in the input that evokes the occurrence of an event of interest. Event arguments are then extracted with respect to the trigger. Indeed, triggers are treated as integral to, and trigger detection as an essential component of, event extraction. In this paper, we provide the first investigation of the role of triggers for the more difficult and much less studied task of document-level event extraction. We analyze their usefulness in multiple end-to-end and pipelined neural event extraction models for three document-level event extraction datasets, measuring performance using triggers of varying quality (human-annotated, LLM-generated, keyword-based, and random). Our research shows that trigger effectiveness varies based on the extraction task's characteristics and data quality, with basic, automatically-generated triggers serving as a viable alternative to human-annotated ones. Furthermore, providing detailed event descriptions to the extraction model helps maintain robust performance even when trigger quality degrades. Perhaps surprisingly, we also find that the mere existence of trigger input, even random ones, is important for prompt-based LLM approaches to the task.