Evaluation

If you’ve ever watched a web agent swing from elegant reasoning to face‑plants on basic facts, you’ve met the limits of outcome‑only training. Atom‑Searcher proposes a simple but radical fix: stop treating the whole reasoning trace as one monolith. Instead, break it down into Atomic Thoughts—the minimal, functional units of reasoning—and supervise them directly with a Reasoning Reward Model (RRM). Then blend those process‑level rewards with the final answer score using a decaying curriculum. The result? More stable training, deeper search behavior, and better generalization across in‑ and out‑of‑domain QA. ...

The one-sentence take A new live benchmark, FutureX, swaps lab-style trivia for rolling, real-world future events, forcing agentic LLMs to search, reason, and hedge under uncertainty that actually moves—and the results expose where today’s “agents” are still brittle. Why FutureX matters now Enterprise teams are deploying agents to answer questions whose truth changes by the hour—markets, elections, sports, product launches. Static leaderboards don’t measure that. FutureX runs as a cron job on reality: it collects new events every day, has agents make predictions, and grades them after events resolve. That turns evaluation from a screenshot into a time series and makes overfitting to benchmark quirks a lot harder. ...

The gist A new clinical natural language inference (NLI) benchmark isolates what models know from how they reason—and the results are stark. State‑of‑the‑art LLMs ace targeted fact checks (≈92% accuracy) but crater on the actual reasoning tasks (≈25% accuracy). The collapse is most extreme in compositional grounding (≈4% accuracy), where a claim depends on multiple interacting clinical constraints (e.g., drug × dose × diagnosis × schedule). Scaling yielded fluent prose, not reliable inference. ...

When language models battle, their strategies talk back. In a controlled Pokémon tournament, eight LLMs drafted teams, chose moves, and logged natural‑language rationales every turn. Beyond win–loss records, those explanations exposed how models reason about uncertainty, risk, and resource management—exactly the traits we want in enterprise decision agents. Why Pokémon is a serious benchmark (yes, really) Pokémon delivers the trifecta we rarely get in classic AI games: Structured complexity: 18 interacting types, clear multipliers, and crisp rules. Uncertainty that matters: imperfect information, status effects, and accuracy trade‑offs. Resource management: limited switches, finite HP, role specialization. Crucially, the action space is compact enough for language-first agents to reason step‑by‑step without search trees—so we can see the strategy, not just the score. ...

If today’s AI models can ace bar exams, explain astrophysics, and generate functional code from a napkin sketch, why do they still fail at seemingly simple questions that require looking and thinking? A new benchmark called MCORE (Multimodal Chain-of-Reasoning Evaluation) answers that question with a resounding: because reasoning across modalities is hard—and we’re not as far along as we thought. Beyond Pattern Matching: What MCORE Tests The majority of multimodal evaluations today rely on either: ...

For all the hype about model accuracy, inference cost, and latency, most organizations are still squinting at scatter plots to decide which large language model (LLM) to use. But what if we could cut through the tradeoff fog with a single number that tells you exactly which model is worth deploying—for your use case, under your constraints? That’s the bold proposal in a recent paper by Zellinger and Thomson from Caltech: treat LLM selection as an economic decision. Rather than searching for models on the accuracy-cost “Pareto frontier,” they suggest an approach grounded in price-tagging errors, delays, and abstentions in dollar terms. Think of it as a model selection framework that answers: How much is a mistake worth to you? ...

If you’ve looked at any leaderboard lately—from SWE-Bench to WebArena—you’ve probably seen impressive numbers. But how many of those reflect real capabilities of AI agents? This paper by Zhu et al. makes a bold claim: agentic benchmarks are often broken, and the way we evaluate AI agents is riddled with systemic flaws. Their response is refreshingly practical: a 33-point diagnostic called the Agentic Benchmark Checklist (ABC), designed not just to critique, but to fix the evaluation process. It’s a must-read not only for benchmark creators, but for any team serious about deploying or comparing AI agents in real-world tasks. ...