Epi2Diff framework uses LLM reasoning traces to predict human item difficulty in educational assessment
Researchers introduce Epi2Diff (Episode to Difficulty), a framework that parses Large Reasoning Model (LRM) reasoning traces into structured cognitive episode sequences to predict how difficult test items are for humans. The approach extracts features from reasoning dynamics—effort allocation, state transitions, iteration patterns—and combines them with semantic item representations. Experiments on four real-world difficulty datasets, including SAT-derived benchmarks, show an 8.1% average relative gain over supervised LLM fine-tuning baselines. The work provides interpretable process evidence for educational measurement without requiring costly human calibration.
Related guides (1)
Related events (8)
EDIT framework trains more rubric-faithful LLM graders via internal-state diagnostics
Researchers introduce Evidence-Diagnosed Intervention Training (EDIT), a two-phase framework for improving LLM-based rubric grading. The first phase (EDIT-SFT) identifies problematic reasoning steps using posterior belief signals and input-grounding scores, then revises only those steps with rubric checklists; the second phase (EDIT-RL) uses belief-guided reward shaping to penalize harmful belief drifts during RL. Experiments on two real-world multi-subject grading benchmarks show consistent improvements over SFT and RL baselines on both in-domain and out-of-domain splits.
ExpRL: RL-based mid-training using human QA data as reward scaffolds for LLM reasoning
ExpRL proposes an automated approach to LLM mid-training that replaces manually curated reasoning traces with large corpora of human-written QA data used as reward scaffolds rather than imitation targets. Reference solutions are hidden from the policy and used only to construct problem-specific grading rubrics, enabling dense process-level rewards that reinforce partial progress and intermediate reasoning steps. On challenging math reasoning benchmarks, ExpRL outperforms SFT, sparse-reward GRPO, and self-distillation as an RL initialization strategy, with additional mixed-domain experiments suggesting broader applicability.
Reasoning in Memory (RiM): Latent Reasoning via Working Memory Blocks in LLMs
RiM introduces a latent reasoning method that replaces autoregressive chain-of-thought token generation with fixed sequences of special 'memory block' tokens, allowing LLMs to perform internal computation without externalizing intermediate steps. These memory blocks are processed in a single forward pass rather than generated autoregressively, improving compute efficiency at test time. Training uses a two-stage curriculum: first grounding memory blocks by predicting explicit reasoning steps, then discarding step-level supervision and refining answers iteratively. Experiments across multiple model families and sizes show RiM matches or exceeds existing latent reasoning methods.
NPHardEval Leaderboard: Benchmarking LLM Reasoning via Computational Complexity Classes
The NPHardEval leaderboard evaluates large language models on reasoning tasks drawn from computational complexity classes (P, NP, NP-Hard), providing a structured framework for assessing algorithmic reasoning capabilities. The benchmark uses dynamic problem updates to mitigate data contamination, a persistent challenge in static benchmarks. Results are hosted on Hugging Face and aim to reveal systematic differences in how frontier models handle problems of varying computational hardness.
ETCHR: Decoupled Image Editing for Visual Chain-of-Thought Reasoning in MLLMs
ETCHR introduces a question-conditioned, reasoning-aware image editing model that decouples visual transformation from downstream understanding in multimodal LLMs. It addresses two identified gaps—language-side (mapping abstract questions to visual edits) and generation-side (edit quality degrading with reasoning depth)—via a two-stage training recipe combining supervised fine-tuning on edit trajectories and VLM-derived reward signals. Because the editor is decoupled, it plugs into arbitrary MLLMs without retraining, yielding Pass@1 gains of roughly +4.6 to +5.5 points across five task families when paired with Qwen3-VL-8B, Gemini-3.1-Flash-Lite, and Kimi K2.5. The work advances the 'think with images' paradigm beyond fixed toolkits and unified multimodal approaches.
Study compares human and LLM active causal reasoning, finding LLMs less efficient but near human-level on conjunctive rules
A new arXiv paper investigates whether active exploration reduces the 'conjunctive handicap' in causal learning, using a blicket detector task with adult participants who could freely intervene to identify causal objects. Results show active exploration substantially improves human conjunctive causal reasoning, though conjunctive rules still require more tests than disjunctive ones. State-of-the-art LLMs approach human-level hypothesis inference accuracy but show less efficient exploration strategies and similar conjunctive-disjunctive performance gaps, raising questions about the nature of LLM causal reasoning.
Dep-LLM: Training-free depression diagnosis framework using structured multi-factor LLM reasoning
Dep-LLM is a training-free framework for automatic depression detection from clinical interviews that uses frozen foundation LLMs without fine-tuning. The system decomposes long clinical dialogues into five thematic factors via Chain-of-Thought analysis, applies token-level entropy-based confidence modulation, and integrates multi-factor signals for final diagnosis. Evaluated on DAIC-WOZ and E-DAIC datasets, it outperforms zero-shot baselines across 21 foundation LLMs and surpasses supervised domain-specific and commercial LLMs on multiple metrics.
DEFINED: Data-efficient framework for fine-grained creativity assessment in debate using LLMs
DEFINED is a computational framework for automated creativity assessment in debate scenarios, operationalizing creativity through an eight-dimensional hierarchical metric system implemented via a pretrained autoregressive language model with a hierarchical scoring head. The system addresses data scarcity through constrained data augmentation and mixed-granularity training from limited expert-annotated data. It outperforms prompt-based LLM evaluators and existing debate scoring methods on authentic competition data. The work is relevant to AI evaluation methodology and the broader question of whether LLMs can reliably assess complex human cognitive outputs.